Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2586 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3546. Min Range: -5.3546
Max Act: 5.3546. Min Act: -0.1700
Data Index: 5593108 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3546. Min Range: -5.3546
Max Act: 5.1983. Min Act: -0.1700
Data Index: 4309846 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3546. Min Range: -5.3546
Max Act: 5.2296. Min Act: -0.1700
Data Index: 6072658 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3546. Min Range: -5.3546
Max Act: 5.1671. Min Act: -0.1700
Data Index: 8306766 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3546. Min Range: -5.3546
Max Act: 5.1671. Min Act: -0.1700
Data Index: 6423735 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3546. Min Range: -5.3546
Max Act: 5.1671. Min Act: -0.1700
Data Index: 7197968 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3546. Min Range: -5.3546
Max Act: 5.1358. Min Act: -0.1700
Data Index: 2826453 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3546. Min Range: -5.3546
Max Act: 5.1358. Min Act: -0.1700
Data Index: 5158316 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3546. Min Range: -5.3546
Max Act: 5.0733. Min Act: -0.1700
Data Index: 4067319 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3546. Min Range: -5.3546
Max Act: 5.0421. Min Act: -0.1700
Data Index: 7017981 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3546. Min Range: -5.3546
Max Act: 5.0108. Min Act: -0.1700
Data Index: 5269773 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3546. Min Range: -5.3546
Max Act: 5.0108. Min Act: -0.1700
Data Index: 1380765 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3546. Min Range: -5.3546
Max Act: 4.9796. Min Act: -0.1700
Data Index: 3984475 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3546. Min Range: -5.3546
Max Act: 4.9796. Min Act: -0.1700
Data Index: 1685178 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3546. Min Range: -5.3546
Max Act: 4.9483. Min Act: -0.1700
Data Index: 5917625 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3546. Min Range: -5.3546
Max Act: 4.9796. Min Act: -0.1700
Data Index: 8576272 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3546. Min Range: -5.3546
Max Act: 4.9796. Min Act: -0.1700
Data Index: 7091908 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3546. Min Range: -5.3546
Max Act: 4.9796. Min Act: -0.1700
Data Index: 8399372 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3546. Min Range: -5.3546
Max Act: 4.9796. Min Act: -0.1700
Data Index: 1179350 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3546. Min Range: -5.3546
Max Act: 4.9483. Min Act: -0.1700
Data Index: 899242 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19