Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2930 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1144. Min Range: -8.1144
Max Act: 8.1144. Min Act: -0.1700
Data Index: 8389439 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1144. Min Range: -8.1144
Max Act: 8.1144. Min Act: -0.1700
Data Index: 45965 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1144. Min Range: -8.1144
Max Act: 7.9894. Min Act: -0.1700
Data Index: 2800362 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1144. Min Range: -8.1144
Max Act: 7.9269. Min Act: -0.1700
Data Index: 1332777 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1144. Min Range: -8.1144
Max Act: 7.8019. Min Act: -0.1700
Data Index: 5515234 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1144. Min Range: -8.1144
Max Act: 7.8019. Min Act: -0.1700
Data Index: 2633931 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1144. Min Range: -8.1144
Max Act: 7.8019. Min Act: -0.1700
Data Index: 2234915 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1144. Min Range: -8.1144
Max Act: 7.7081. Min Act: -0.1700
Data Index: 4291661 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1144. Min Range: -8.1144
Max Act: 7.6769. Min Act: -0.1700
Data Index: 2895783 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1144. Min Range: -8.1144
Max Act: 7.6769. Min Act: -0.1700
Data Index: 4513479 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1144. Min Range: -8.1144
Max Act: 7.6769. Min Act: -0.1700
Data Index: 3631254 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1144. Min Range: -8.1144
Max Act: 7.6769. Min Act: -0.1700
Data Index: 7801893 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1144. Min Range: -8.1144
Max Act: 7.6144. Min Act: -0.1700
Data Index: 8202945 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1144. Min Range: -8.1144
Max Act: 7.6144. Min Act: -0.1700
Data Index: 1127428 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1144. Min Range: -8.1144
Max Act: 7.5831. Min Act: -0.1700
Data Index: 6766398 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1144. Min Range: -8.1144
Max Act: 7.5206. Min Act: -0.1700
Data Index: 5390840 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1144. Min Range: -8.1144
Max Act: 7.5206. Min Act: -0.1700
Data Index: 2068790 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1144. Min Range: -8.1144
Max Act: 7.5206. Min Act: -0.1700
Data Index: 7709255 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1144. Min Range: -8.1144
Max Act: 7.4894. Min Act: -0.1700
Data Index: 5167807 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1144. Min Range: -8.1144
Max Act: 7.4894. Min Act: -0.1700
Data Index: 2908801 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19