Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1256 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8265. Min Range: -3.8265
Max Act: 3.8265. Min Act: -0.1700
Data Index: 3297199 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8265. Min Range: -3.8265
Max Act: 3.6858. Min Act: -0.1700
Data Index: 456724 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8265. Min Range: -3.8265
Max Act: 3.6701. Min Act: -0.1700
Data Index: 2395028 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8265. Min Range: -3.8265
Max Act: 3.6701. Min Act: -0.1700
Data Index: 1477516 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8265. Min Range: -3.8265
Max Act: 3.6545. Min Act: -0.1700
Data Index: 4051129 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8265. Min Range: -3.8265
Max Act: 3.6545. Min Act: -0.1700
Data Index: 2011207 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8265. Min Range: -3.8265
Max Act: 3.6232. Min Act: -0.1700
Data Index: 3212840 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8265. Min Range: -3.8265
Max Act: 3.6232. Min Act: -0.1700
Data Index: 8128637 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8265. Min Range: -3.8265
Max Act: 3.5919. Min Act: -0.1700
Data Index: 4258170 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8265. Min Range: -3.8265
Max Act: 3.5762. Min Act: -0.1700
Data Index: 8256364 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8265. Min Range: -3.8265
Max Act: 3.5606. Min Act: -0.1700
Data Index: 801540 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8265. Min Range: -3.8265
Max Act: 3.5292. Min Act: -0.1700
Data Index: 5240268 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8265. Min Range: -3.8265
Max Act: 3.5449. Min Act: -0.1700
Data Index: 5527527 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8265. Min Range: -3.8265
Max Act: 3.5449. Min Act: -0.1700
Data Index: 377303 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8265. Min Range: -3.8265
Max Act: 3.5449. Min Act: -0.1700
Data Index: 7139556 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8265. Min Range: -3.8265
Max Act: 3.5449. Min Act: -0.1700
Data Index: 5014793 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8265. Min Range: -3.8265
Max Act: 3.5292. Min Act: -0.1700
Data Index: 4257785 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8265. Min Range: -3.8265
Max Act: 3.4979. Min Act: -0.1700
Data Index: 7790998 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8265. Min Range: -3.8265
Max Act: 3.5292. Min Act: -0.1700
Data Index: 3779317 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8265. Min Range: -3.8265
Max Act: 3.4979. Min Act: -0.1700
Data Index: 683942 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19