Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1636 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1070. Min Range: -8.1070
Max Act: 8.1070. Min Act: -0.1700
Data Index: 4558089 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1070. Min Range: -8.1070
Max Act: 8.0757. Min Act: -0.1700
Data Index: 8045744 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1070. Min Range: -8.1070
Max Act: 7.9820. Min Act: -0.1700
Data Index: 504333 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1070. Min Range: -8.1070
Max Act: 7.8882. Min Act: -0.1700
Data Index: 2410952 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1070. Min Range: -8.1070
Max Act: 7.7320. Min Act: -0.1700
Data Index: 8045746 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1070. Min Range: -8.1070
Max Act: 7.7320. Min Act: -0.1700
Data Index: 4453382 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1070. Min Range: -8.1070
Max Act: 7.7320. Min Act: -0.1700
Data Index: 2691327 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1070. Min Range: -8.1070
Max Act: 7.7007. Min Act: -0.1700
Data Index: 239585 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1070. Min Range: -8.1070
Max Act: 7.7007. Min Act: -0.1700
Data Index: 8333421 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1070. Min Range: -8.1070
Max Act: 7.7007. Min Act: -0.1700
Data Index: 3079037 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1070. Min Range: -8.1070
Max Act: 7.6382. Min Act: -0.1700
Data Index: 4558094 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1070. Min Range: -8.1070
Max Act: 7.6695. Min Act: -0.1700
Data Index: 3012480 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1070. Min Range: -8.1070
Max Act: 7.6070. Min Act: -0.1700
Data Index: 1857252 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1070. Min Range: -8.1070
Max Act: 7.6382. Min Act: -0.1700
Data Index: 6774264 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1070. Min Range: -8.1070
Max Act: 7.6070. Min Act: -0.1700
Data Index: 5565962 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1070. Min Range: -8.1070
Max Act: 7.5757. Min Act: -0.1700
Data Index: 2158722 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1070. Min Range: -8.1070
Max Act: 7.5757. Min Act: -0.1700
Data Index: 632357 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1070. Min Range: -8.1070
Max Act: 7.6070. Min Act: -0.1700
Data Index: 4960632 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1070. Min Range: -8.1070
Max Act: 7.6070. Min Act: -0.1700
Data Index: 6478239 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1070. Min Range: -8.1070
Max Act: 7.5757. Min Act: -0.1700
Data Index: 1817945 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19