Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2229 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1417. Min Range: -4.1417
Max Act: 4.1417. Min Act: -0.1700
Data Index: 6830394 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1417. Min Range: -4.1417
Max Act: 4.0479. Min Act: -0.1700
Data Index: 5972376 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1417. Min Range: -4.1417
Max Act: 4.0167. Min Act: -0.1700
Data Index: 8286783 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1417. Min Range: -4.1417
Max Act: 3.9854. Min Act: -0.1700
Data Index: 3685316 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1417. Min Range: -4.1417
Max Act: 3.9229. Min Act: -0.1700
Data Index: 586467 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1417. Min Range: -4.1417
Max Act: 3.9541. Min Act: -0.1700
Data Index: 3526612 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1417. Min Range: -4.1417
Max Act: 3.9229. Min Act: -0.1700
Data Index: 5650306 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1417. Min Range: -4.1417
Max Act: 3.9229. Min Act: -0.1700
Data Index: 4836517 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1417. Min Range: -4.1417
Max Act: 3.9229. Min Act: -0.1700
Data Index: 5525292 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1417. Min Range: -4.1417
Max Act: 3.8916. Min Act: -0.1700
Data Index: 8161695 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1417. Min Range: -4.1417
Max Act: 3.8916. Min Act: -0.1700
Data Index: 7552281 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1417. Min Range: -4.1417
Max Act: 3.8604. Min Act: -0.1700
Data Index: 410188 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1417. Min Range: -4.1417
Max Act: 3.8604. Min Act: -0.1700
Data Index: 8611471 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1417. Min Range: -4.1417
Max Act: 3.7978. Min Act: -0.1700
Data Index: 3526613 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1417. Min Range: -4.1417
Max Act: 3.8916. Min Act: -0.1700
Data Index: 8404922 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1417. Min Range: -4.1417
Max Act: 3.8604. Min Act: -0.1700
Data Index: 6336718 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1417. Min Range: -4.1417
Max Act: 3.7978. Min Act: -0.1700
Data Index: 5114433 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1417. Min Range: -4.1417
Max Act: 3.7665. Min Act: -0.1700
Data Index: 668743 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1417. Min Range: -4.1417
Max Act: 3.7665. Min Act: -0.1700
Data Index: 911352 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1417. Min Range: -4.1417
Max Act: 3.7978. Min Act: -0.1700
Data Index: 4176277 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19