Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3458 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3026. Min Range: -7.3026
Max Act: 7.3026. Min Act: -0.1700
Data Index: 2581038 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3026. Min Range: -7.3026
Max Act: 7.1776. Min Act: -0.1700
Data Index: 5685365 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3026. Min Range: -7.3026
Max Act: 7.1151. Min Act: -0.1700
Data Index: 5595987 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3026. Min Range: -7.3026
Max Act: 7.1151. Min Act: -0.1700
Data Index: 5083800 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3026. Min Range: -7.3026
Max Act: 7.1151. Min Act: -0.1700
Data Index: 4322511 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3026. Min Range: -7.3026
Max Act: 7.1151. Min Act: -0.1700
Data Index: 6090099 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3026. Min Range: -7.3026
Max Act: 7.0526. Min Act: -0.1700
Data Index: 1680940 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3026. Min Range: -7.3026
Max Act: 7.0526. Min Act: -0.1700
Data Index: 3166113 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3026. Min Range: -7.3026
Max Act: 7.0526. Min Act: -0.1700
Data Index: 3641278 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3026. Min Range: -7.3026
Max Act: 7.0526. Min Act: -0.1700
Data Index: 4698815 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3026. Min Range: -7.3026
Max Act: 7.0526. Min Act: -0.1700
Data Index: 574533 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3026. Min Range: -7.3026
Max Act: 6.9901. Min Act: -0.1700
Data Index: 7964571 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3026. Min Range: -7.3026
Max Act: 6.9901. Min Act: -0.1700
Data Index: 2167242 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3026. Min Range: -7.3026
Max Act: 6.9901. Min Act: -0.1700
Data Index: 3041305 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3026. Min Range: -7.3026
Max Act: 6.9276. Min Act: -0.1700
Data Index: 1126843 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3026. Min Range: -7.3026
Max Act: 6.9276. Min Act: -0.1700
Data Index: 7463018 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3026. Min Range: -7.3026
Max Act: 6.9276. Min Act: -0.1700
Data Index: 1422368 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3026. Min Range: -7.3026
Max Act: 6.9276. Min Act: -0.1700
Data Index: 5782722 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3026. Min Range: -7.3026
Max Act: 6.9276. Min Act: -0.1700
Data Index: 2336661 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3026. Min Range: -7.3026
Max Act: 6.9276. Min Act: -0.1700
Data Index: 341308 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19