Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2736 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9837. Min Range: -3.9837
Max Act: 3.9837. Min Act: -0.1700
Data Index: 3543439 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9837. Min Range: -3.9837
Max Act: 3.9212. Min Act: -0.1700
Data Index: 7906787 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9837. Min Range: -3.9837
Max Act: 3.9212. Min Act: -0.1700
Data Index: 3088342 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9837. Min Range: -3.9837
Max Act: 3.7961. Min Act: -0.1700
Data Index: 3088343 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9837. Min Range: -3.9837
Max Act: 3.7023. Min Act: -0.1700
Data Index: 8671715 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9837. Min Range: -3.9837
Max Act: 3.7023. Min Act: -0.1700
Data Index: 921320 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9837. Min Range: -3.9837
Max Act: 3.6397. Min Act: -0.1700
Data Index: 5615304 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9837. Min Range: -3.9837
Max Act: 3.6084. Min Act: -0.1700
Data Index: 8663762 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9837. Min Range: -3.9837
Max Act: 3.6397. Min Act: -0.1700
Data Index: 6120229 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9837. Min Range: -3.9837
Max Act: 3.6397. Min Act: -0.1700
Data Index: 4596430 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9837. Min Range: -3.9837
Max Act: 3.6084. Min Act: -0.1700
Data Index: 671156 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9837. Min Range: -3.9837
Max Act: 3.6084. Min Act: -0.1700
Data Index: 3551339 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9837. Min Range: -3.9837
Max Act: 3.5771. Min Act: -0.1700
Data Index: 4132702 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9837. Min Range: -3.9837
Max Act: 3.5458. Min Act: -0.1700
Data Index: 1369729 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9837. Min Range: -3.9837
Max Act: 3.5458. Min Act: -0.1700
Data Index: 1326299 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9837. Min Range: -3.9837
Max Act: 3.5458. Min Act: -0.1700
Data Index: 3059082 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9837. Min Range: -3.9837
Max Act: 3.5145. Min Act: -0.1700
Data Index: 651158 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9837. Min Range: -3.9837
Max Act: 3.4832. Min Act: -0.1700
Data Index: 6332897 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9837. Min Range: -3.9837
Max Act: 3.4832. Min Act: -0.1700
Data Index: 7159695 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9837. Min Range: -3.9837
Max Act: 3.4832. Min Act: -0.1700
Data Index: 7779002 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19