Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 455 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.6199. Min Act: -0.1700
Data Index: 4991853 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.5574. Min Act: -0.1700
Data Index: 1610207 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.4949. Min Act: -0.1700
Data Index: 5056605 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.4324. Min Act: -0.1700
Data Index: 7407090 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.4324. Min Act: -0.1700
Data Index: 5034490 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.3386. Min Act: -0.1700
Data Index: 4892209 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.3074. Min Act: -0.1700
Data Index: 8133940 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.3386. Min Act: -0.1700
Data Index: 480244 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.3074. Min Act: -0.1700
Data Index: 6140248 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.3074. Min Act: -0.1700
Data Index: 6526170 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.2449. Min Act: -0.1700
Data Index: 6682183 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.2449. Min Act: -0.1700
Data Index: 7705054 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.2761. Min Act: -0.1700
Data Index: 1110508 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.2449. Min Act: -0.1700
Data Index: 2366414 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.2449. Min Act: -0.1700
Data Index: 5951940 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.2449. Min Act: -0.1700
Data Index: 4969389 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.2449. Min Act: -0.1700
Data Index: 8655286 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.2136. Min Act: -0.1700
Data Index: 7257587 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.2136. Min Act: -0.1700
Data Index: 2978290 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.2136. Min Act: -0.1700
Data Index: 3888625 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #19