Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 435 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6613. Min Range: -6.6613
Max Act: 6.6613. Min Act: -0.1700
Data Index: 2944241 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6613. Min Range: -6.6613
Max Act: 6.5050. Min Act: -0.1700
Data Index: 7296001 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6613. Min Range: -6.6613
Max Act: 6.3800. Min Act: -0.1700
Data Index: 5736740 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6613. Min Range: -6.6613
Max Act: 6.3488. Min Act: -0.1700
Data Index: 2940733 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6613. Min Range: -6.6613
Max Act: 6.2863. Min Act: -0.1700
Data Index: 2390911 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6613. Min Range: -6.6613
Max Act: 6.2863. Min Act: -0.1700
Data Index: 5307882 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6613. Min Range: -6.6613
Max Act: 6.2238. Min Act: -0.1700
Data Index: 5493454 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6613. Min Range: -6.6613
Max Act: 6.2238. Min Act: -0.1700
Data Index: 4013120 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6613. Min Range: -6.6613
Max Act: 6.1613. Min Act: -0.1700
Data Index: 7572512 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6613. Min Range: -6.6613
Max Act: 6.1925. Min Act: -0.1700
Data Index: 7572513 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6613. Min Range: -6.6613
Max Act: 6.1613. Min Act: -0.1700
Data Index: 7137725 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6613. Min Range: -6.6613
Max Act: 6.1613. Min Act: -0.1700
Data Index: 3899175 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6613. Min Range: -6.6613
Max Act: 6.1613. Min Act: -0.1700
Data Index: 3181263 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6613. Min Range: -6.6613
Max Act: 6.1300. Min Act: -0.1700
Data Index: 4006048 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6613. Min Range: -6.6613
Max Act: 6.1613. Min Act: -0.1700
Data Index: 433907 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6613. Min Range: -6.6613
Max Act: 6.0988. Min Act: -0.1700
Data Index: 1464544 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6613. Min Range: -6.6613
Max Act: 6.0675. Min Act: -0.1700
Data Index: 4099000 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6613. Min Range: -6.6613
Max Act: 6.0363. Min Act: -0.1700
Data Index: 1742524 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6613. Min Range: -6.6613
Max Act: 6.0675. Min Act: -0.1700
Data Index: 3627610 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6613. Min Range: -6.6613
Max Act: 6.0988. Min Act: -0.1700
Data Index: 215596 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19