Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2839 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9321. Min Range: -8.9321
Max Act: 8.9321. Min Act: -0.1700
Data Index: 4570258 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9321. Min Range: -8.9321
Max Act: 8.7446. Min Act: -0.1700
Data Index: 6479891 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9321. Min Range: -8.9321
Max Act: 8.4321. Min Act: -0.1700
Data Index: 4799287 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9321. Min Range: -8.9321
Max Act: 8.2446. Min Act: -0.1700
Data Index: 7807177 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9321. Min Range: -8.9321
Max Act: 8.2446. Min Act: -0.1700
Data Index: 654695 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9321. Min Range: -8.9321
Max Act: 8.2446. Min Act: -0.1700
Data Index: 2726112 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9321. Min Range: -8.9321
Max Act: 8.1821. Min Act: -0.1700
Data Index: 4638911 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9321. Min Range: -8.9321
Max Act: 8.1196. Min Act: -0.1700
Data Index: 7845900 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9321. Min Range: -8.9321
Max Act: 8.1196. Min Act: -0.1700
Data Index: 149380 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9321. Min Range: -8.9321
Max Act: 8.1196. Min Act: -0.1700
Data Index: 8132535 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9321. Min Range: -8.9321
Max Act: 8.1196. Min Act: -0.1700
Data Index: 6397851 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9321. Min Range: -8.9321
Max Act: 8.0571. Min Act: -0.1700
Data Index: 8370028 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9321. Min Range: -8.9321
Max Act: 8.0571. Min Act: -0.1700
Data Index: 2273881 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9321. Min Range: -8.9321
Max Act: 7.9946. Min Act: -0.1700
Data Index: 5733791 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9321. Min Range: -8.9321
Max Act: 7.9946. Min Act: -0.1700
Data Index: 8134118 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9321. Min Range: -8.9321
Max Act: 7.9946. Min Act: -0.1700
Data Index: 2819594 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9321. Min Range: -8.9321
Max Act: 7.9946. Min Act: -0.1700
Data Index: 833128 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9321. Min Range: -8.9321
Max Act: 7.9946. Min Act: -0.1700
Data Index: 2026130 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9321. Min Range: -8.9321
Max Act: 8.0571. Min Act: -0.1700
Data Index: 3664894 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9321. Min Range: -8.9321
Max Act: 7.9946. Min Act: -0.1700
Data Index: 7329878 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19