Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 772 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1525. Min Range: -3.1525
Max Act: 3.1525. Min Act: -0.1700
Data Index: 1618006 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1525. Min Range: -3.1525
Max Act: 3.0422. Min Act: -0.1700
Data Index: 2494771 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1525. Min Range: -3.1525
Max Act: 2.9948. Min Act: -0.1700
Data Index: 8078855 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1525. Min Range: -3.1525
Max Act: 3.0106. Min Act: -0.1700
Data Index: 7980281 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1525. Min Range: -3.1525
Max Act: 2.9790. Min Act: -0.1700
Data Index: 6638336 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1525. Min Range: -3.1525
Max Act: 2.9474. Min Act: -0.1700
Data Index: 219785 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1525. Min Range: -3.1525
Max Act: 2.9632. Min Act: -0.1700
Data Index: 2126476 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1525. Min Range: -3.1525
Max Act: 2.9632. Min Act: -0.1700
Data Index: 202116 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1525. Min Range: -3.1525
Max Act: 2.9632. Min Act: -0.1700
Data Index: 7233326 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1525. Min Range: -3.1525
Max Act: 2.9632. Min Act: -0.1700
Data Index: 827880 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1525. Min Range: -3.1525
Max Act: 2.9474. Min Act: -0.1700
Data Index: 7134203 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1525. Min Range: -3.1525
Max Act: 2.9315. Min Act: -0.1700
Data Index: 189414 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1525. Min Range: -3.1525
Max Act: 2.9157. Min Act: -0.1700
Data Index: 3838584 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1525. Min Range: -3.1525
Max Act: 2.9315. Min Act: -0.1700
Data Index: 5417168 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1525. Min Range: -3.1525
Max Act: 2.9315. Min Act: -0.1700
Data Index: 7627743 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1525. Min Range: -3.1525
Max Act: 2.9315. Min Act: -0.1700
Data Index: 3473262 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1525. Min Range: -3.1525
Max Act: 2.9157. Min Act: -0.1700
Data Index: 6532619 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1525. Min Range: -3.1525
Max Act: 2.8681. Min Act: -0.1700
Data Index: 3057776 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1525. Min Range: -3.1525
Max Act: 2.8998. Min Act: -0.1700
Data Index: 7484450 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1525. Min Range: -3.1525
Max Act: 2.8522. Min Act: -0.1700
Data Index: 4817183 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19