Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3105 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4739. Min Range: -6.4739
Max Act: 6.4739. Min Act: -0.1700
Data Index: 190138 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4739. Min Range: -6.4739
Max Act: 6.4426. Min Act: -0.1700
Data Index: 3730377 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4739. Min Range: -6.4739
Max Act: 6.2239. Min Act: -0.1700
Data Index: 7210387 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4739. Min Range: -6.4739
Max Act: 6.2239. Min Act: -0.1700
Data Index: 8585241 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4739. Min Range: -6.4739
Max Act: 6.0989. Min Act: -0.1700
Data Index: 190139 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4739. Min Range: -6.4739
Max Act: 6.0989. Min Act: -0.1700
Data Index: 7210388 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4739. Min Range: -6.4739
Max Act: 5.9426. Min Act: -0.1700
Data Index: 4459687 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4739. Min Range: -6.4739
Max Act: 5.8801. Min Act: -0.1700
Data Index: 2424305 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4739. Min Range: -6.4739
Max Act: 5.8801. Min Act: -0.1700
Data Index: 1890829 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4739. Min Range: -6.4739
Max Act: 5.8176. Min Act: -0.1700
Data Index: 987887 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4739. Min Range: -6.4739
Max Act: 5.8489. Min Act: -0.1700
Data Index: 8588108 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4739. Min Range: -6.4739
Max Act: 5.8176. Min Act: -0.1700
Data Index: 8629245 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4739. Min Range: -6.4739
Max Act: 5.7551. Min Act: -0.1700
Data Index: 7351676 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4739. Min Range: -6.4739
Max Act: 5.7239. Min Act: -0.1700
Data Index: 5692717 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4739. Min Range: -6.4739
Max Act: 5.7551. Min Act: -0.1700
Data Index: 5832413 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4739. Min Range: -6.4739
Max Act: 5.7239. Min Act: -0.1700
Data Index: 6083435 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4739. Min Range: -6.4739
Max Act: 5.7239. Min Act: -0.1700
Data Index: 8321793 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4739. Min Range: -6.4739
Max Act: 5.6926. Min Act: -0.1700
Data Index: 8016144 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4739. Min Range: -6.4739
Max Act: 5.6301. Min Act: -0.1700
Data Index: 2124792 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4739. Min Range: -6.4739
Max Act: 5.6614. Min Act: -0.1700
Data Index: 1487534 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19