Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3425 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0695. Min Range: -6.0695
Max Act: 6.0695. Min Act: -0.1700
Data Index: 1752083 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0695. Min Range: -6.0695
Max Act: 5.9133. Min Act: -0.1700
Data Index: 4085546 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0695. Min Range: -6.0695
Max Act: 5.8195. Min Act: -0.1700
Data Index: 5277651 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0695. Min Range: -6.0695
Max Act: 5.7883. Min Act: -0.1700
Data Index: 2519235 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0695. Min Range: -6.0695
Max Act: 5.7570. Min Act: -0.1700
Data Index: 8544485 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0695. Min Range: -6.0695
Max Act: 5.7883. Min Act: -0.1700
Data Index: 4085549 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0695. Min Range: -6.0695
Max Act: 5.7570. Min Act: -0.1700
Data Index: 1389372 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0695. Min Range: -6.0695
Max Act: 5.7570. Min Act: -0.1700
Data Index: 8766691 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0695. Min Range: -6.0695
Max Act: 5.7258. Min Act: -0.1700
Data Index: 115850 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0695. Min Range: -6.0695
Max Act: 5.7258. Min Act: -0.1700
Data Index: 3878179 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0695. Min Range: -6.0695
Max Act: 5.6945. Min Act: -0.1700
Data Index: 5853771 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0695. Min Range: -6.0695
Max Act: 5.6945. Min Act: -0.1700
Data Index: 563467 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0695. Min Range: -6.0695
Max Act: 5.6633. Min Act: -0.1700
Data Index: 2828177 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0695. Min Range: -6.0695
Max Act: 5.6633. Min Act: -0.1700
Data Index: 6306845 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0695. Min Range: -6.0695
Max Act: 5.6633. Min Act: -0.1700
Data Index: 4085548 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0695. Min Range: -6.0695
Max Act: 5.6633. Min Act: -0.1700
Data Index: 5384 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0695. Min Range: -6.0695
Max Act: 5.6633. Min Act: -0.1700
Data Index: 7268332 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0695. Min Range: -6.0695
Max Act: 5.6320. Min Act: -0.1700
Data Index: 2779 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0695. Min Range: -6.0695
Max Act: 5.6320. Min Act: -0.1700
Data Index: 345798 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0695. Min Range: -6.0695
Max Act: 5.6320. Min Act: -0.1700
Data Index: 7766609 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19