Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1326 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.7273. Min Range: -7.7273
Max Act: 7.7273. Min Act: -0.1700
Data Index: 6098912 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7273. Min Range: -7.7273
Max Act: 7.6336. Min Act: -0.1700
Data Index: 8137037 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7273. Min Range: -7.7273
Max Act: 7.6023. Min Act: -0.1700
Data Index: 5148665 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7273. Min Range: -7.7273
Max Act: 7.5086. Min Act: -0.1700
Data Index: 7635116 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7273. Min Range: -7.7273
Max Act: 7.4461. Min Act: -0.1700
Data Index: 1736623 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7273. Min Range: -7.7273
Max Act: 7.2898. Min Act: -0.1700
Data Index: 3268847 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7273. Min Range: -7.7273
Max Act: 7.3211. Min Act: -0.1700
Data Index: 3948770 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7273. Min Range: -7.7273
Max Act: 7.2586. Min Act: -0.1700
Data Index: 5723188 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7273. Min Range: -7.7273
Max Act: 7.2898. Min Act: -0.1700
Data Index: 5861281 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7273. Min Range: -7.7273
Max Act: 7.1961. Min Act: -0.1700
Data Index: 6360909 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7273. Min Range: -7.7273
Max Act: 7.2273. Min Act: -0.1700
Data Index: 5845453 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7273. Min Range: -7.7273
Max Act: 7.1336. Min Act: -0.1700
Data Index: 4101742 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7273. Min Range: -7.7273
Max Act: 7.1648. Min Act: -0.1700
Data Index: 432310 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7273. Min Range: -7.7273
Max Act: 7.1648. Min Act: -0.1700
Data Index: 6234564 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7273. Min Range: -7.7273
Max Act: 7.1023. Min Act: -0.1700
Data Index: 5525492 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7273. Min Range: -7.7273
Max Act: 7.0398. Min Act: -0.1700
Data Index: 554829 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7273. Min Range: -7.7273
Max Act: 7.0086. Min Act: -0.1700
Data Index: 6066548 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7273. Min Range: -7.7273
Max Act: 7.1336. Min Act: -0.1700
Data Index: 7773142 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7273. Min Range: -7.7273
Max Act: 7.0711. Min Act: -0.1700
Data Index: 5939669 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7273. Min Range: -7.7273
Max Act: 7.0398. Min Act: -0.1700
Data Index: 6750060 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19