Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3099 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3478. Min Range: -9.3478
Max Act: 9.3478. Min Act: -0.1700
Data Index: 6325066 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3478. Min Range: -9.3478
Max Act: 8.9728. Min Act: -0.1700
Data Index: 4830247 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3478. Min Range: -9.3478
Max Act: 8.9103. Min Act: -0.1700
Data Index: 5145289 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3478. Min Range: -9.3478
Max Act: 8.9103. Min Act: -0.1700
Data Index: 5730077 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3478. Min Range: -9.3478
Max Act: 8.9103. Min Act: -0.1700
Data Index: 3450165 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3478. Min Range: -9.3478
Max Act: 8.7853. Min Act: -0.1700
Data Index: 594990 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3478. Min Range: -9.3478
Max Act: 8.7228. Min Act: -0.1700
Data Index: 3671304 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3478. Min Range: -9.3478
Max Act: 8.7228. Min Act: -0.1700
Data Index: 5607186 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3478. Min Range: -9.3478
Max Act: 8.7228. Min Act: -0.1700
Data Index: 238441 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3478. Min Range: -9.3478
Max Act: 8.7228. Min Act: -0.1700
Data Index: 2675762 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3478. Min Range: -9.3478
Max Act: 8.6603. Min Act: -0.1700
Data Index: 7804303 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3478. Min Range: -9.3478
Max Act: 8.6603. Min Act: -0.1700
Data Index: 4236952 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3478. Min Range: -9.3478
Max Act: 8.5353. Min Act: -0.1700
Data Index: 5557534 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3478. Min Range: -9.3478
Max Act: 8.5353. Min Act: -0.1700
Data Index: 6921942 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3478. Min Range: -9.3478
Max Act: 8.4728. Min Act: -0.1700
Data Index: 1118004 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3478. Min Range: -9.3478
Max Act: 8.5353. Min Act: -0.1700
Data Index: 863909 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3478. Min Range: -9.3478
Max Act: 8.5353. Min Act: -0.1700
Data Index: 3863991 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3478. Min Range: -9.3478
Max Act: 8.5353. Min Act: -0.1700
Data Index: 3505690 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3478. Min Range: -9.3478
Max Act: 8.4728. Min Act: -0.1700
Data Index: 7031841 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3478. Min Range: -9.3478
Max Act: 8.4728. Min Act: -0.1700
Data Index: 5183138 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19