Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5634 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7102. Min Range: -8.7102
Max Act: 8.7102. Min Act: -0.1700
Data Index: 3307203 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7102. Min Range: -8.7102
Max Act: 8.4602. Min Act: -0.1700
Data Index: 2972220 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7102. Min Range: -8.7102
Max Act: 8.3977. Min Act: -0.1700
Data Index: 1764059 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7102. Min Range: -8.7102
Max Act: 8.3977. Min Act: -0.1700
Data Index: 892044 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7102. Min Range: -8.7102
Max Act: 8.3352. Min Act: -0.1700
Data Index: 5267347 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7102. Min Range: -8.7102
Max Act: 8.3977. Min Act: -0.1700
Data Index: 4045437 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7102. Min Range: -8.7102
Max Act: 8.3352. Min Act: -0.1700
Data Index: 8067182 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7102. Min Range: -8.7102
Max Act: 8.3352. Min Act: -0.1700
Data Index: 8061751 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7102. Min Range: -8.7102
Max Act: 8.2727. Min Act: -0.1700
Data Index: 6061301 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7102. Min Range: -8.7102
Max Act: 8.3352. Min Act: -0.1700
Data Index: 8676212 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7102. Min Range: -8.7102
Max Act: 8.2727. Min Act: -0.1700
Data Index: 7228874 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7102. Min Range: -8.7102
Max Act: 8.2727. Min Act: -0.1700
Data Index: 4294755 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7102. Min Range: -8.7102
Max Act: 8.2102. Min Act: -0.1700
Data Index: 3590906 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7102. Min Range: -8.7102
Max Act: 8.2102. Min Act: -0.1700
Data Index: 1502407 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7102. Min Range: -8.7102
Max Act: 8.2102. Min Act: -0.1700
Data Index: 7311341 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7102. Min Range: -8.7102
Max Act: 8.2102. Min Act: -0.1700
Data Index: 2191982 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7102. Min Range: -8.7102
Max Act: 8.2102. Min Act: -0.1700
Data Index: 1239511 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7102. Min Range: -8.7102
Max Act: 8.2102. Min Act: -0.1700
Data Index: 3841972 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7102. Min Range: -8.7102
Max Act: 8.1477. Min Act: -0.1700
Data Index: 4823315 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7102. Min Range: -8.7102
Max Act: 8.0852. Min Act: -0.1700
Data Index: 4993658 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #19