Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 835 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9229. Min Range: -5.9229
Max Act: 5.9229. Min Act: -0.1700
Data Index: 951523 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9229. Min Range: -5.9229
Max Act: 5.7354. Min Act: -0.1700
Data Index: 4954438 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9229. Min Range: -5.9229
Max Act: 5.4229. Min Act: -0.1700
Data Index: 8506034 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9229. Min Range: -5.9229
Max Act: 5.2042. Min Act: -0.1700
Data Index: 8149921 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9229. Min Range: -5.9229
Max Act: 5.1729. Min Act: -0.1700
Data Index: 5925903 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9229. Min Range: -5.9229
Max Act: 5.1417. Min Act: -0.1700
Data Index: 5958895 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9229. Min Range: -5.9229
Max Act: 5.1104. Min Act: -0.1700
Data Index: 7068091 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9229. Min Range: -5.9229
Max Act: 5.1417. Min Act: -0.1700
Data Index: 5944534 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9229. Min Range: -5.9229
Max Act: 5.1104. Min Act: -0.1700
Data Index: 1967640 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9229. Min Range: -5.9229
Max Act: 5.0479. Min Act: -0.1700
Data Index: 5928277 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9229. Min Range: -5.9229
Max Act: 5.0167. Min Act: -0.1700
Data Index: 8122467 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9229. Min Range: -5.9229
Max Act: 4.9854. Min Act: -0.1700
Data Index: 8413937 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9229. Min Range: -5.9229
Max Act: 4.9542. Min Act: -0.1700
Data Index: 8719479 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9229. Min Range: -5.9229
Max Act: 4.9542. Min Act: -0.1700
Data Index: 1226240 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9229. Min Range: -5.9229
Max Act: 4.9542. Min Act: -0.1700
Data Index: 4238915 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9229. Min Range: -5.9229
Max Act: 4.9542. Min Act: -0.1700
Data Index: 1694691 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9229. Min Range: -5.9229
Max Act: 4.9542. Min Act: -0.1700
Data Index: 617953 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9229. Min Range: -5.9229
Max Act: 4.9229. Min Act: -0.1700
Data Index: 6141791 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9229. Min Range: -5.9229
Max Act: 4.8917. Min Act: -0.1700
Data Index: 1633043 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9229. Min Range: -5.9229
Max Act: 4.8604. Min Act: -0.1700
Data Index: 600278 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19