Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3187 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4643. Min Range: -5.4643
Max Act: 5.4643. Min Act: -0.1700
Data Index: 3378019 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4643. Min Range: -5.4643
Max Act: 5.3080. Min Act: -0.1700
Data Index: 89606 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4643. Min Range: -5.4643
Max Act: 5.2455. Min Act: -0.1700
Data Index: 4206728 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4643. Min Range: -5.4643
Max Act: 5.2455. Min Act: -0.1700
Data Index: 5819883 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4643. Min Range: -5.4643
Max Act: 5.2143. Min Act: -0.1700
Data Index: 6867503 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4643. Min Range: -5.4643
Max Act: 5.1830. Min Act: -0.1700
Data Index: 2062358 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4643. Min Range: -5.4643
Max Act: 5.1205. Min Act: -0.1700
Data Index: 5935888 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4643. Min Range: -5.4643
Max Act: 5.1205. Min Act: -0.1700
Data Index: 1038118 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4643. Min Range: -5.4643
Max Act: 5.1205. Min Act: -0.1700
Data Index: 6489572 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4643. Min Range: -5.4643
Max Act: 5.1205. Min Act: -0.1700
Data Index: 776535 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4643. Min Range: -5.4643
Max Act: 5.1205. Min Act: -0.1700
Data Index: 8806453 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4643. Min Range: -5.4643
Max Act: 5.1205. Min Act: -0.1700
Data Index: 5976164 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4643. Min Range: -5.4643
Max Act: 5.0893. Min Act: -0.1700
Data Index: 140840 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4643. Min Range: -5.4643
Max Act: 5.0893. Min Act: -0.1700
Data Index: 8599714 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4643. Min Range: -5.4643
Max Act: 5.0893. Min Act: -0.1700
Data Index: 3666583 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4643. Min Range: -5.4643
Max Act: 5.0893. Min Act: -0.1700
Data Index: 5649099 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4643. Min Range: -5.4643
Max Act: 5.0580. Min Act: -0.1700
Data Index: 4293941 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4643. Min Range: -5.4643
Max Act: 5.0580. Min Act: -0.1700
Data Index: 5856903 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4643. Min Range: -5.4643
Max Act: 5.0580. Min Act: -0.1700
Data Index: 745470 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4643. Min Range: -5.4643
Max Act: 5.0268. Min Act: -0.1700
Data Index: 3103068 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19