Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4436 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.5174. Min Act: -0.1700
Data Index: 1164543 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.4862. Min Act: -0.1700
Data Index: 538409 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.4549. Min Act: -0.1700
Data Index: 1142448 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.4862. Min Act: -0.1700
Data Index: 1535638 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.4237. Min Act: -0.1700
Data Index: 7738428 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.3299. Min Act: -0.1700
Data Index: 2341698 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.3612. Min Act: -0.1700
Data Index: 5308365 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.3612. Min Act: -0.1700
Data Index: 5297696 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.3299. Min Act: -0.1700
Data Index: 4650727 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.3299. Min Act: -0.1700
Data Index: 3567187 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.2987. Min Act: -0.1700
Data Index: 2247994 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.2987. Min Act: -0.1700
Data Index: 5157453 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.2674. Min Act: -0.1700
Data Index: 3108442 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.2674. Min Act: -0.1700
Data Index: 5335739 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.2362. Min Act: -0.1700
Data Index: 2413400 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.2362. Min Act: -0.1700
Data Index: 5291414 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.2049. Min Act: -0.1700
Data Index: 6689446 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.2049. Min Act: -0.1700
Data Index: 964982 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.2049. Min Act: -0.1700
Data Index: 4297974 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.2049. Min Act: -0.1700
Data Index: 6548048 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19