Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3650 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.3154. Min Range: -1.3154
Max Act: 1.3154. Min Act: -0.1694
Data Index: 4306327 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3154. Min Range: -1.3154
Max Act: 1.3154. Min Act: -0.1700
Data Index: 3246366 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3154. Min Range: -1.3154
Max Act: 1.2890. Min Act: -0.1691
Data Index: 3925 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3154. Min Range: -1.3154
Max Act: 1.2978. Min Act: -0.1700
Data Index: 287463 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3154. Min Range: -1.3154
Max Act: 1.2890. Min Act: -0.1699
Data Index: 7969814 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3154. Min Range: -1.3154
Max Act: 1.2801. Min Act: -0.1693
Data Index: 2609424 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3154. Min Range: -1.3154
Max Act: 1.2713. Min Act: -0.1700
Data Index: 5995275 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3154. Min Range: -1.3154
Max Act: 1.2713. Min Act: -0.1672
Data Index: 2743534 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3154. Min Range: -1.3154
Max Act: 1.2713. Min Act: -0.1693
Data Index: 3118932 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3154. Min Range: -1.3154
Max Act: 1.2625. Min Act: -0.1697
Data Index: 5860553 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3154. Min Range: -1.3154
Max Act: 1.2625. Min Act: -0.1700
Data Index: 2711854 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3154. Min Range: -1.3154
Max Act: 1.2625. Min Act: -0.1700
Data Index: 456599 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3154. Min Range: -1.3154
Max Act: 1.2625. Min Act: -0.1700
Data Index: 1311770 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3154. Min Range: -1.3154
Max Act: 1.2625. Min Act: -0.1700
Data Index: 6654775 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3154. Min Range: -1.3154
Max Act: 1.2625. Min Act: -0.1599
Data Index: 3396180 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3154. Min Range: -1.3154
Max Act: 1.2625. Min Act: -0.1700
Data Index: 3616864 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3154. Min Range: -1.3154
Max Act: 1.2625. Min Act: -0.1700
Data Index: 8123434 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3154. Min Range: -1.3154
Max Act: 1.2537. Min Act: -0.1689
Data Index: 8246259 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3154. Min Range: -1.3154
Max Act: 1.2625. Min Act: -0.1700
Data Index: 2574993 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3154. Min Range: -1.3154
Max Act: 1.2537. Min Act: -0.1697
Data Index: 4668664 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19