Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3843 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 12.4920. Min Range: -12.4920
Max Act: 12.4920. Min Act: -0.1700
Data Index: 4483856 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.4920. Min Range: -12.4920
Max Act: 12.3045. Min Act: -0.1700
Data Index: 3205781 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.4920. Min Range: -12.4920
Max Act: 12.2420. Min Act: -0.1700
Data Index: 3727546 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.4920. Min Range: -12.4920
Max Act: 12.2420. Min Act: -0.1700
Data Index: 7963235 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.4920. Min Range: -12.4920
Max Act: 12.1170. Min Act: -0.1700
Data Index: 496000 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.4920. Min Range: -12.4920
Max Act: 11.9295. Min Act: -0.1700
Data Index: 8048031 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.4920. Min Range: -12.4920
Max Act: 11.8045. Min Act: -0.1700
Data Index: 6285392 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.4920. Min Range: -12.4920
Max Act: 11.8670. Min Act: -0.1700
Data Index: 795184 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.4920. Min Range: -12.4920
Max Act: 11.7420. Min Act: -0.1700
Data Index: 1947941 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.4920. Min Range: -12.4920
Max Act: 11.6795. Min Act: -0.1700
Data Index: 2761114 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.4920. Min Range: -12.4920
Max Act: 11.6795. Min Act: -0.1700
Data Index: 3414795 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.4920. Min Range: -12.4920
Max Act: 11.6170. Min Act: -0.1700
Data Index: 7037874 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.4920. Min Range: -12.4920
Max Act: 11.6170. Min Act: -0.1700
Data Index: 1984634 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.4920. Min Range: -12.4920
Max Act: 11.6170. Min Act: -0.1700
Data Index: 4831166 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.4920. Min Range: -12.4920
Max Act: 11.6170. Min Act: -0.1700
Data Index: 890460 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.4920. Min Range: -12.4920
Max Act: 11.5545. Min Act: -0.1700
Data Index: 1248176 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.4920. Min Range: -12.4920
Max Act: 11.5545. Min Act: -0.1700
Data Index: 1320109 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.4920. Min Range: -12.4920
Max Act: 11.5545. Min Act: -0.1700
Data Index: 6267127 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.4920. Min Range: -12.4920
Max Act: 11.5545. Min Act: -0.1700
Data Index: 2313245 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.4920. Min Range: -12.4920
Max Act: 11.4920. Min Act: -0.1700
Data Index: 2364423 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19