Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 661 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7274. Min Range: -5.7274
Max Act: 5.7274. Min Act: -0.1700
Data Index: 4975480 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7274. Min Range: -5.7274
Max Act: 5.6962. Min Act: -0.1700
Data Index: 5470596 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7274. Min Range: -5.7274
Max Act: 5.5087. Min Act: -0.1700
Data Index: 4149033 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7274. Min Range: -5.7274
Max Act: 5.4774. Min Act: -0.1700
Data Index: 2598783 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7274. Min Range: -5.7274
Max Act: 5.4462. Min Act: -0.1700
Data Index: 3495482 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7274. Min Range: -5.7274
Max Act: 5.4149. Min Act: -0.1700
Data Index: 2526698 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7274. Min Range: -5.7274
Max Act: 5.4149. Min Act: -0.1700
Data Index: 1757938 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7274. Min Range: -5.7274
Max Act: 5.4149. Min Act: -0.1700
Data Index: 6630477 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7274. Min Range: -5.7274
Max Act: 5.4149. Min Act: -0.1700
Data Index: 3328667 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7274. Min Range: -5.7274
Max Act: 5.3837. Min Act: -0.1700
Data Index: 4801665 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7274. Min Range: -5.7274
Max Act: 5.3837. Min Act: -0.1700
Data Index: 1927915 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7274. Min Range: -5.7274
Max Act: 5.3524. Min Act: -0.1700
Data Index: 2301553 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7274. Min Range: -5.7274
Max Act: 5.3524. Min Act: -0.1700
Data Index: 5387741 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7274. Min Range: -5.7274
Max Act: 5.3524. Min Act: -0.1700
Data Index: 267075 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7274. Min Range: -5.7274
Max Act: 5.3212. Min Act: -0.1700
Data Index: 3659259 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7274. Min Range: -5.7274
Max Act: 5.3212. Min Act: -0.1700
Data Index: 1998899 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7274. Min Range: -5.7274
Max Act: 5.3212. Min Act: -0.1700
Data Index: 6375839 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7274. Min Range: -5.7274
Max Act: 5.3212. Min Act: -0.1700
Data Index: 2802042 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7274. Min Range: -5.7274
Max Act: 5.2899. Min Act: -0.1700
Data Index: 26714 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7274. Min Range: -5.7274
Max Act: 5.3212. Min Act: -0.1700
Data Index: 2903090 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19