Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3826 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1715. Min Range: -6.1715
Max Act: 6.1715. Min Act: -0.1700
Data Index: 8059860 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1715. Min Range: -6.1715
Max Act: 5.8590. Min Act: -0.1700
Data Index: 620833 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1715. Min Range: -6.1715
Max Act: 5.8278. Min Act: -0.1700
Data Index: 3556814 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1715. Min Range: -6.1715
Max Act: 5.7340. Min Act: -0.1700
Data Index: 7822134 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1715. Min Range: -6.1715
Max Act: 5.6715. Min Act: -0.1700
Data Index: 7824461 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1715. Min Range: -6.1715
Max Act: 5.6090. Min Act: -0.1700
Data Index: 1275306 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1715. Min Range: -6.1715
Max Act: 5.5778. Min Act: -0.1700
Data Index: 8254040 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1715. Min Range: -6.1715
Max Act: 5.5465. Min Act: -0.1700
Data Index: 3778202 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1715. Min Range: -6.1715
Max Act: 5.5465. Min Act: -0.1700
Data Index: 549130 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1715. Min Range: -6.1715
Max Act: 5.5465. Min Act: -0.1700
Data Index: 3023135 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1715. Min Range: -6.1715
Max Act: 5.5153. Min Act: -0.1700
Data Index: 3095919 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1715. Min Range: -6.1715
Max Act: 5.4840. Min Act: -0.1700
Data Index: 5512049 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1715. Min Range: -6.1715
Max Act: 5.4840. Min Act: -0.1700
Data Index: 486750 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1715. Min Range: -6.1715
Max Act: 5.5153. Min Act: -0.1700
Data Index: 6657135 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1715. Min Range: -6.1715
Max Act: 5.4528. Min Act: -0.1700
Data Index: 8582066 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1715. Min Range: -6.1715
Max Act: 5.4528. Min Act: -0.1700
Data Index: 2085938 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1715. Min Range: -6.1715
Max Act: 5.4528. Min Act: -0.1700
Data Index: 8592135 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1715. Min Range: -6.1715
Max Act: 5.4528. Min Act: -0.1700
Data Index: 948800 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1715. Min Range: -6.1715
Max Act: 5.4215. Min Act: -0.1700
Data Index: 2871297 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1715. Min Range: -6.1715
Max Act: 5.3903. Min Act: -0.1700
Data Index: 3662298 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19