Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3126 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4370. Min Range: -5.4370
Max Act: 5.4370. Min Act: -0.1700
Data Index: 3784928 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4370. Min Range: -5.4370
Max Act: 5.3120. Min Act: -0.1700
Data Index: 2766865 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4370. Min Range: -5.4370
Max Act: 5.1870. Min Act: -0.1700
Data Index: 3915238 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4370. Min Range: -5.4370
Max Act: 5.1557. Min Act: -0.1700
Data Index: 7837332 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4370. Min Range: -5.4370
Max Act: 5.0307. Min Act: -0.1700
Data Index: 5829621 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4370. Min Range: -5.4370
Max Act: 5.0307. Min Act: -0.1700
Data Index: 8147445 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4370. Min Range: -5.4370
Max Act: 5.0307. Min Act: -0.1700
Data Index: 4589017 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4370. Min Range: -5.4370
Max Act: 4.9682. Min Act: -0.1700
Data Index: 6878718 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4370. Min Range: -5.4370
Max Act: 4.9370. Min Act: -0.1700
Data Index: 4083464 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4370. Min Range: -5.4370
Max Act: 4.9370. Min Act: -0.1700
Data Index: 2242659 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4370. Min Range: -5.4370
Max Act: 4.9370. Min Act: -0.1700
Data Index: 2145530 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4370. Min Range: -5.4370
Max Act: 4.9370. Min Act: -0.1700
Data Index: 3733875 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4370. Min Range: -5.4370
Max Act: 4.9057. Min Act: -0.1700
Data Index: 8476524 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4370. Min Range: -5.4370
Max Act: 4.8745. Min Act: -0.1700
Data Index: 8081997 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4370. Min Range: -5.4370
Max Act: 4.8745. Min Act: -0.1700
Data Index: 8481869 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4370. Min Range: -5.4370
Max Act: 4.9057. Min Act: -0.1700
Data Index: 3258836 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4370. Min Range: -5.4370
Max Act: 4.8745. Min Act: -0.1700
Data Index: 502501 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4370. Min Range: -5.4370
Max Act: 4.8432. Min Act: -0.1700
Data Index: 3863770 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4370. Min Range: -5.4370
Max Act: 4.8432. Min Act: -0.1700
Data Index: 4082285 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4370. Min Range: -5.4370
Max Act: 4.8432. Min Act: -0.1700
Data Index: 6851035 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19