Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3320 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.5104. Min Act: -0.1700
Data Index: 2653204 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.3854. Min Act: -0.1700
Data Index: 6277724 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.3541. Min Act: -0.1700
Data Index: 1724592 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.2916. Min Act: -0.1700
Data Index: 7779210 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.2291. Min Act: -0.1700
Data Index: 7044601 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.1979. Min Act: -0.1700
Data Index: 1882816 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.1979. Min Act: -0.1700
Data Index: 6468036 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.1979. Min Act: -0.1700
Data Index: 382773 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.1666. Min Act: -0.1700
Data Index: 7680940 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.1979. Min Act: -0.1700
Data Index: 1110614 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.1666. Min Act: -0.1700
Data Index: 1199089 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.1666. Min Act: -0.1700
Data Index: 2701045 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.1666. Min Act: -0.1700
Data Index: 7929541 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.1666. Min Act: -0.1700
Data Index: 6389255 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.1041. Min Act: -0.1700
Data Index: 3051081 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.1354. Min Act: -0.1700
Data Index: 4974122 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.1354. Min Act: -0.1700
Data Index: 5794243 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.1354. Min Act: -0.1700
Data Index: 7143354 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.1354. Min Act: -0.1700
Data Index: 1390496 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.1041. Min Act: -0.1700
Data Index: 1414331 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19