Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2602 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.8481. Min Act: -0.1700
Data Index: 1325422 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.7231. Min Act: -0.1700
Data Index: 2095230 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.6606. Min Act: -0.1700
Data Index: 652791 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.6918. Min Act: -0.1700
Data Index: 5696925 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.6606. Min Act: -0.1700
Data Index: 6970665 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.6293. Min Act: -0.1700
Data Index: 8057423 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.6293. Min Act: -0.1700
Data Index: 890751 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.6293. Min Act: -0.1700
Data Index: 5206792 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.5668. Min Act: -0.1700
Data Index: 2806470 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.5356. Min Act: -0.1700
Data Index: 5689814 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.5356. Min Act: -0.1700
Data Index: 265392 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.5668. Min Act: -0.1700
Data Index: 7658511 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.5668. Min Act: -0.1700
Data Index: 8067750 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.5356. Min Act: -0.1700
Data Index: 6154647 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.5356. Min Act: -0.1700
Data Index: 3221130 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.5043. Min Act: -0.1700
Data Index: 3717664 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.5043. Min Act: -0.1700
Data Index: 5520667 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.5356. Min Act: -0.1700
Data Index: 4981406 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.5043. Min Act: -0.1700
Data Index: 6253458 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.5043. Min Act: -0.1700
Data Index: 5718527 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19