Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1728 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.3614. Min Act: -0.1700
Data Index: 786051 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.2989. Min Act: -0.1700
Data Index: 7730276 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.2989. Min Act: -0.1700
Data Index: 3285385 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.2364. Min Act: -0.1700
Data Index: 804243 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.2364. Min Act: -0.1700
Data Index: 4338060 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.1739. Min Act: -0.1700
Data Index: 7850903 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.1739. Min Act: -0.1700
Data Index: 8317986 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.1739. Min Act: -0.1700
Data Index: 2319232 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.2051. Min Act: -0.1700
Data Index: 1752834 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.1739. Min Act: -0.1700
Data Index: 3776077 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.1426. Min Act: -0.1700
Data Index: 3446653 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.1426. Min Act: -0.1700
Data Index: 6563518 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.1426. Min Act: -0.1700
Data Index: 6707788 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.0801. Min Act: -0.1700
Data Index: 3220378 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.1114. Min Act: -0.1700
Data Index: 590624 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.1426. Min Act: -0.1700
Data Index: 2738092 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.0801. Min Act: -0.1700
Data Index: 2419453 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.0489. Min Act: -0.1700
Data Index: 8113668 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.1114. Min Act: -0.1700
Data Index: 7432217 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.0489. Min Act: -0.1700
Data Index: 6137425 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19