Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1712 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5302. Min Range: -5.5302
Max Act: 5.5302. Min Act: -0.1700
Data Index: 1627447 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5302. Min Range: -5.5302
Max Act: 5.4364. Min Act: -0.1700
Data Index: 2478303 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5302. Min Range: -5.5302
Max Act: 5.3739. Min Act: -0.1700
Data Index: 751742 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5302. Min Range: -5.5302
Max Act: 5.3427. Min Act: -0.1700
Data Index: 198518 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5302. Min Range: -5.5302
Max Act: 5.2489. Min Act: -0.1700
Data Index: 2690779 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5302. Min Range: -5.5302
Max Act: 5.2177. Min Act: -0.1700
Data Index: 1406975 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5302. Min Range: -5.5302
Max Act: 5.2177. Min Act: -0.1700
Data Index: 5378848 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5302. Min Range: -5.5302
Max Act: 5.1552. Min Act: -0.1700
Data Index: 881596 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5302. Min Range: -5.5302
Max Act: 5.1864. Min Act: -0.1700
Data Index: 4555956 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5302. Min Range: -5.5302
Max Act: 5.1552. Min Act: -0.1700
Data Index: 8678929 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5302. Min Range: -5.5302
Max Act: 5.1239. Min Act: -0.1700
Data Index: 3831624 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5302. Min Range: -5.5302
Max Act: 5.0927. Min Act: -0.1700
Data Index: 3342237 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5302. Min Range: -5.5302
Max Act: 5.0614. Min Act: -0.1700
Data Index: 104603 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5302. Min Range: -5.5302
Max Act: 5.0302. Min Act: -0.1700
Data Index: 3423996 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5302. Min Range: -5.5302
Max Act: 5.0614. Min Act: -0.1700
Data Index: 1406966 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5302. Min Range: -5.5302
Max Act: 5.0614. Min Act: -0.1700
Data Index: 4899889 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5302. Min Range: -5.5302
Max Act: 5.0614. Min Act: -0.1700
Data Index: 7929966 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5302. Min Range: -5.5302
Max Act: 5.0302. Min Act: -0.1700
Data Index: 1490765 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5302. Min Range: -5.5302
Max Act: 5.0302. Min Act: -0.1700
Data Index: 1406953 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5302. Min Range: -5.5302
Max Act: 4.9989. Min Act: -0.1700
Data Index: 8114587 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19