Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3005 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8495. Min Range: -4.8495
Max Act: 4.8495. Min Act: -0.1700
Data Index: 358464 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8495. Min Range: -4.8495
Max Act: 4.7557. Min Act: -0.1700
Data Index: 5477079 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8495. Min Range: -4.8495
Max Act: 4.6620. Min Act: -0.1700
Data Index: 2142970 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8495. Min Range: -4.8495
Max Act: 4.6307. Min Act: -0.1700
Data Index: 682945 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8495. Min Range: -4.8495
Max Act: 4.6307. Min Act: -0.1700
Data Index: 7379948 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8495. Min Range: -4.8495
Max Act: 4.6307. Min Act: -0.1700
Data Index: 7490016 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8495. Min Range: -4.8495
Max Act: 4.6307. Min Act: -0.1700
Data Index: 669210 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8495. Min Range: -4.8495
Max Act: 4.5682. Min Act: -0.1700
Data Index: 8138666 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8495. Min Range: -4.8495
Max Act: 4.5682. Min Act: -0.1700
Data Index: 2093174 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8495. Min Range: -4.8495
Max Act: 4.5370. Min Act: -0.1700
Data Index: 3817722 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8495. Min Range: -4.8495
Max Act: 4.5682. Min Act: -0.1700
Data Index: 3066231 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8495. Min Range: -4.8495
Max Act: 4.5682. Min Act: -0.1700
Data Index: 2682305 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8495. Min Range: -4.8495
Max Act: 4.5370. Min Act: -0.1700
Data Index: 17788 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8495. Min Range: -4.8495
Max Act: 4.5370. Min Act: -0.1700
Data Index: 8422554 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8495. Min Range: -4.8495
Max Act: 4.5370. Min Act: -0.1700
Data Index: 6344379 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8495. Min Range: -4.8495
Max Act: 4.5057. Min Act: -0.1700
Data Index: 332677 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8495. Min Range: -4.8495
Max Act: 4.5057. Min Act: -0.1700
Data Index: 699392 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8495. Min Range: -4.8495
Max Act: 4.4745. Min Act: -0.1700
Data Index: 7118567 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8495. Min Range: -4.8495
Max Act: 4.4745. Min Act: -0.1700
Data Index: 7841874 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8495. Min Range: -4.8495
Max Act: 4.4745. Min Act: -0.1700
Data Index: 5021971 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19