Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2911 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9295. Min Range: -5.9295
Max Act: 5.9295. Min Act: -0.1700
Data Index: 4724164 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9295. Min Range: -5.9295
Max Act: 5.8045. Min Act: -0.1700
Data Index: 8488040 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9295. Min Range: -5.9295
Max Act: 5.7108. Min Act: -0.1700
Data Index: 8693796 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9295. Min Range: -5.9295
Max Act: 5.6483. Min Act: -0.1700
Data Index: 4628509 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9295. Min Range: -5.9295
Max Act: 5.6170. Min Act: -0.1700
Data Index: 2912581 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9295. Min Range: -5.9295
Max Act: 5.5858. Min Act: -0.1700
Data Index: 7754322 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9295. Min Range: -5.9295
Max Act: 5.5858. Min Act: -0.1700
Data Index: 3809617 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9295. Min Range: -5.9295
Max Act: 5.5233. Min Act: -0.1700
Data Index: 6457188 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9295. Min Range: -5.9295
Max Act: 5.4295. Min Act: -0.1700
Data Index: 1797217 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9295. Min Range: -5.9295
Max Act: 5.3358. Min Act: -0.1700
Data Index: 7646316 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9295. Min Range: -5.9295
Max Act: 5.3670. Min Act: -0.1700
Data Index: 4849010 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9295. Min Range: -5.9295
Max Act: 5.3358. Min Act: -0.1700
Data Index: 2419011 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9295. Min Range: -5.9295
Max Act: 5.3358. Min Act: -0.1700
Data Index: 8512892 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9295. Min Range: -5.9295
Max Act: 5.3358. Min Act: -0.1700
Data Index: 5194903 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9295. Min Range: -5.9295
Max Act: 5.3358. Min Act: -0.1700
Data Index: 3906518 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9295. Min Range: -5.9295
Max Act: 5.3045. Min Act: -0.1700
Data Index: 7179380 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9295. Min Range: -5.9295
Max Act: 5.3045. Min Act: -0.1700
Data Index: 3575219 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9295. Min Range: -5.9295
Max Act: 5.2733. Min Act: -0.1700
Data Index: 7293649 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9295. Min Range: -5.9295
Max Act: 5.2733. Min Act: -0.1700
Data Index: 7138379 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9295. Min Range: -5.9295
Max Act: 5.2420. Min Act: -0.1700
Data Index: 4241204 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #19