Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3086 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.4152. Min Range: -1.4152
Max Act: 1.4152. Min Act: -0.1700
Data Index: 2318941 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4152. Min Range: -1.4152
Max Act: 1.3359. Min Act: -0.1700
Data Index: 2327677 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4152. Min Range: -1.4152
Max Act: 1.3182. Min Act: -0.1700
Data Index: 1262615 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4152. Min Range: -1.4152
Max Act: 1.3182. Min Act: -0.1699
Data Index: 2654813 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4152. Min Range: -1.4152
Max Act: 1.2918. Min Act: -0.1700
Data Index: 408820 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4152. Min Range: -1.4152
Max Act: 1.2741. Min Act: -0.1700
Data Index: 6761737 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4152. Min Range: -1.4152
Max Act: 1.2741. Min Act: -0.1700
Data Index: 5301105 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4152. Min Range: -1.4152
Max Act: 1.2653. Min Act: -0.1700
Data Index: 4272328 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4152. Min Range: -1.4152
Max Act: 1.2741. Min Act: -0.1700
Data Index: 1900770 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4152. Min Range: -1.4152
Max Act: 1.2741. Min Act: -0.1700
Data Index: 4846156 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4152. Min Range: -1.4152
Max Act: 1.2653. Min Act: -0.1700
Data Index: 7786838 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4152. Min Range: -1.4152
Max Act: 1.2565. Min Act: -0.1700
Data Index: 3111422 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4152. Min Range: -1.4152
Max Act: 1.2477. Min Act: -0.1700
Data Index: 3687129 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4152. Min Range: -1.4152
Max Act: 1.2741. Min Act: -0.1700
Data Index: 721909 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4152. Min Range: -1.4152
Max Act: 1.2477. Min Act: -0.1700
Data Index: 6759774 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4152. Min Range: -1.4152
Max Act: 1.2477. Min Act: -0.1700
Data Index: 581766 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4152. Min Range: -1.4152
Max Act: 1.2477. Min Act: -0.1700
Data Index: 2080121 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4152. Min Range: -1.4152
Max Act: 1.2653. Min Act: -0.1700
Data Index: 4633319 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4152. Min Range: -1.4152
Max Act: 1.2565. Min Act: -0.1700
Data Index: 4587345 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4152. Min Range: -1.4152
Max Act: 1.2477. Min Act: -0.1700
Data Index: 5048072 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #19