Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3532 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1896. Min Range: -5.1896
Max Act: 5.1896. Min Act: -0.1700
Data Index: 3081204 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1896. Min Range: -5.1896
Max Act: 5.1584. Min Act: -0.1700
Data Index: 6082548 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1896. Min Range: -5.1896
Max Act: 5.1584. Min Act: -0.1700
Data Index: 4227563 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1896. Min Range: -5.1896
Max Act: 5.1584. Min Act: -0.1700
Data Index: 8725800 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1896. Min Range: -5.1896
Max Act: 5.0959. Min Act: -0.1700
Data Index: 7319924 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1896. Min Range: -5.1896
Max Act: 5.0959. Min Act: -0.1700
Data Index: 7319921 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1896. Min Range: -5.1896
Max Act: 5.0334. Min Act: -0.1700
Data Index: 3767992 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1896. Min Range: -5.1896
Max Act: 5.0334. Min Act: -0.1700
Data Index: 2399345 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1896. Min Range: -5.1896
Max Act: 5.0334. Min Act: -0.1700
Data Index: 7487563 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1896. Min Range: -5.1896
Max Act: 5.0021. Min Act: -0.1700
Data Index: 3767993 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1896. Min Range: -5.1896
Max Act: 5.0021. Min Act: -0.1700
Data Index: 3044994 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1896. Min Range: -5.1896
Max Act: 4.9709. Min Act: -0.1700
Data Index: 8725799 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1896. Min Range: -5.1896
Max Act: 4.9709. Min Act: -0.1700
Data Index: 3327517 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1896. Min Range: -5.1896
Max Act: 4.9709. Min Act: -0.1700
Data Index: 3847587 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1896. Min Range: -5.1896
Max Act: 4.9709. Min Act: -0.1700
Data Index: 7721263 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1896. Min Range: -5.1896
Max Act: 4.9084. Min Act: -0.1700
Data Index: 505657 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1896. Min Range: -5.1896
Max Act: 4.9084. Min Act: -0.1700
Data Index: 7418494 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1896. Min Range: -5.1896
Max Act: 4.9084. Min Act: -0.1700
Data Index: 7305923 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1896. Min Range: -5.1896
Max Act: 4.9084. Min Act: -0.1700
Data Index: 3044997 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1896. Min Range: -5.1896
Max Act: 4.9084. Min Act: -0.1700
Data Index: 1023998 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19