Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1551 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.8671. Min Act: -0.1700
Data Index: 5815397 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.8046. Min Act: -0.1700
Data Index: 936307 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.7733. Min Act: -0.1700
Data Index: 2804461 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.7733. Min Act: -0.1700
Data Index: 393516 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.7421. Min Act: -0.1700
Data Index: 7167436 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.7108. Min Act: -0.1700
Data Index: 1775239 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.7108. Min Act: -0.1700
Data Index: 283587 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.7108. Min Act: -0.1700
Data Index: 6143088 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.6483. Min Act: -0.1700
Data Index: 5024196 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.6483. Min Act: -0.1700
Data Index: 6152013 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.6483. Min Act: -0.1700
Data Index: 6521378 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.6483. Min Act: -0.1700
Data Index: 7854773 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.6483. Min Act: -0.1700
Data Index: 7812589 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.6796. Min Act: -0.1700
Data Index: 292439 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.6483. Min Act: -0.1700
Data Index: 5658632 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.6483. Min Act: -0.1700
Data Index: 7401111 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.6171. Min Act: -0.1700
Data Index: 8482154 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.6171. Min Act: -0.1700
Data Index: 4203240 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.6171. Min Act: -0.1700
Data Index: 3808920 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.6171. Min Act: -0.1700
Data Index: 4406062 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19