Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4163 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8024. Min Range: -7.8024
Max Act: 7.8024. Min Act: -0.1700
Data Index: 8400656 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8024. Min Range: -7.8024
Max Act: 7.5837. Min Act: -0.1700
Data Index: 4144484 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8024. Min Range: -7.8024
Max Act: 7.4899. Min Act: -0.1700
Data Index: 6708064 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8024. Min Range: -7.8024
Max Act: 7.3962. Min Act: -0.1700
Data Index: 3716092 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8024. Min Range: -7.8024
Max Act: 7.3649. Min Act: -0.1700
Data Index: 3454040 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8024. Min Range: -7.8024
Max Act: 7.3649. Min Act: -0.1700
Data Index: 5212199 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8024. Min Range: -7.8024
Max Act: 7.2712. Min Act: -0.1700
Data Index: 3312868 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8024. Min Range: -7.8024
Max Act: 7.2399. Min Act: -0.1700
Data Index: 1181041 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8024. Min Range: -7.8024
Max Act: 7.2087. Min Act: -0.1700
Data Index: 3071459 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8024. Min Range: -7.8024
Max Act: 7.2087. Min Act: -0.1700
Data Index: 4361825 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8024. Min Range: -7.8024
Max Act: 7.1774. Min Act: -0.1700
Data Index: 7575999 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8024. Min Range: -7.8024
Max Act: 7.1462. Min Act: -0.1700
Data Index: 2304832 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8024. Min Range: -7.8024
Max Act: 7.1462. Min Act: -0.1700
Data Index: 6456558 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8024. Min Range: -7.8024
Max Act: 7.1149. Min Act: -0.1700
Data Index: 1597648 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8024. Min Range: -7.8024
Max Act: 7.1149. Min Act: -0.1700
Data Index: 2966477 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8024. Min Range: -7.8024
Max Act: 7.0837. Min Act: -0.1700
Data Index: 6740523 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8024. Min Range: -7.8024
Max Act: 7.0837. Min Act: -0.1700
Data Index: 2386843 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8024. Min Range: -7.8024
Max Act: 7.0837. Min Act: -0.1700
Data Index: 316541 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8024. Min Range: -7.8024
Max Act: 7.0524. Min Act: -0.1700
Data Index: 2386841 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8024. Min Range: -7.8024
Max Act: 7.0524. Min Act: -0.1700
Data Index: 1720656 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19