Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3400 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6647. Min Range: -6.6647
Max Act: 6.6647. Min Act: -0.1700
Data Index: 7123165 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6647. Min Range: -6.6647
Max Act: 6.1647. Min Act: -0.1700
Data Index: 6710397 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6647. Min Range: -6.6647
Max Act: 6.1334. Min Act: -0.1700
Data Index: 6916435 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6647. Min Range: -6.6647
Max Act: 5.9772. Min Act: -0.1700
Data Index: 3976987 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6647. Min Range: -6.6647
Max Act: 5.8834. Min Act: -0.1700
Data Index: 2934436 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6647. Min Range: -6.6647
Max Act: 5.8522. Min Act: -0.1700
Data Index: 1405193 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6647. Min Range: -6.6647
Max Act: 5.8522. Min Act: -0.1700
Data Index: 3453809 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6647. Min Range: -6.6647
Max Act: 5.7584. Min Act: -0.1700
Data Index: 6933840 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6647. Min Range: -6.6647
Max Act: 5.7584. Min Act: -0.1700
Data Index: 4917692 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6647. Min Range: -6.6647
Max Act: 5.7272. Min Act: -0.1700
Data Index: 6240316 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6647. Min Range: -6.6647
Max Act: 5.7272. Min Act: -0.1700
Data Index: 159654 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6647. Min Range: -6.6647
Max Act: 5.7272. Min Act: -0.1700
Data Index: 7558331 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6647. Min Range: -6.6647
Max Act: 5.7272. Min Act: -0.1700
Data Index: 159431 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6647. Min Range: -6.6647
Max Act: 5.7272. Min Act: -0.1700
Data Index: 3950589 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6647. Min Range: -6.6647
Max Act: 5.6959. Min Act: -0.1700
Data Index: 210409 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6647. Min Range: -6.6647
Max Act: 5.6647. Min Act: -0.1700
Data Index: 4188312 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6647. Min Range: -6.6647
Max Act: 5.6334. Min Act: -0.1700
Data Index: 7558323 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6647. Min Range: -6.6647
Max Act: 5.6647. Min Act: -0.1700
Data Index: 4606704 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6647. Min Range: -6.6647
Max Act: 5.6334. Min Act: -0.1700
Data Index: 4327652 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6647. Min Range: -6.6647
Max Act: 5.6647. Min Act: -0.1700
Data Index: 2480391 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #19