Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 666 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1407. Min Range: -6.1407
Max Act: 6.1407. Min Act: -0.1700
Data Index: 559457 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1407. Min Range: -6.1407
Max Act: 6.0782. Min Act: -0.1700
Data Index: 3066797 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1407. Min Range: -6.1407
Max Act: 6.0470. Min Act: -0.1700
Data Index: 1210303 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1407. Min Range: -6.1407
Max Act: 6.0470. Min Act: -0.1700
Data Index: 4081398 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1407. Min Range: -6.1407
Max Act: 6.0157. Min Act: -0.1700
Data Index: 2028228 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1407. Min Range: -6.1407
Max Act: 6.0157. Min Act: -0.1700
Data Index: 4360065 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1407. Min Range: -6.1407
Max Act: 6.0157. Min Act: -0.1700
Data Index: 1930253 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1407. Min Range: -6.1407
Max Act: 6.0157. Min Act: -0.1700
Data Index: 6365288 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1407. Min Range: -6.1407
Max Act: 5.9845. Min Act: -0.1700
Data Index: 5645 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1407. Min Range: -6.1407
Max Act: 5.9845. Min Act: -0.1700
Data Index: 2712682 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1407. Min Range: -6.1407
Max Act: 5.9845. Min Act: -0.1700
Data Index: 3960178 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1407. Min Range: -6.1407
Max Act: 5.9845. Min Act: -0.1700
Data Index: 439736 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1407. Min Range: -6.1407
Max Act: 5.9532. Min Act: -0.1700
Data Index: 7569187 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1407. Min Range: -6.1407
Max Act: 5.9532. Min Act: -0.1700
Data Index: 6706097 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1407. Min Range: -6.1407
Max Act: 5.9532. Min Act: -0.1700
Data Index: 776907 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1407. Min Range: -6.1407
Max Act: 5.9532. Min Act: -0.1700
Data Index: 6127478 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1407. Min Range: -6.1407
Max Act: 5.9532. Min Act: -0.1700
Data Index: 4743443 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1407. Min Range: -6.1407
Max Act: 5.9532. Min Act: -0.1700
Data Index: 1653441 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1407. Min Range: -6.1407
Max Act: 5.9532. Min Act: -0.1700
Data Index: 1449285 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1407. Min Range: -6.1407
Max Act: 5.9532. Min Act: -0.1700
Data Index: 4697252 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19