Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3368 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8605. Min Range: -4.8605
Max Act: 4.8605. Min Act: -0.1700
Data Index: 4737551 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8605. Min Range: -4.8605
Max Act: 4.8605. Min Act: -0.1700
Data Index: 3404268 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8605. Min Range: -4.8605
Max Act: 4.8293. Min Act: -0.1700
Data Index: 5634770 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8605. Min Range: -4.8605
Max Act: 4.7355. Min Act: -0.1700
Data Index: 6091075 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8605. Min Range: -4.8605
Max Act: 4.6730. Min Act: -0.1700
Data Index: 1254719 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8605. Min Range: -4.8605
Max Act: 4.6730. Min Act: -0.1700
Data Index: 2483104 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8605. Min Range: -4.8605
Max Act: 4.6418. Min Act: -0.1700
Data Index: 2773644 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8605. Min Range: -4.8605
Max Act: 4.6105. Min Act: -0.1700
Data Index: 5988248 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8605. Min Range: -4.8605
Max Act: 4.6105. Min Act: -0.1700
Data Index: 618340 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8605. Min Range: -4.8605
Max Act: 4.6105. Min Act: -0.1700
Data Index: 1375062 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8605. Min Range: -4.8605
Max Act: 4.5793. Min Act: -0.1700
Data Index: 262503 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8605. Min Range: -4.8605
Max Act: 4.5793. Min Act: -0.1700
Data Index: 2726406 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8605. Min Range: -4.8605
Max Act: 4.5793. Min Act: -0.1700
Data Index: 1357494 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8605. Min Range: -4.8605
Max Act: 4.5480. Min Act: -0.1700
Data Index: 2180893 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8605. Min Range: -4.8605
Max Act: 4.5793. Min Act: -0.1700
Data Index: 7481254 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8605. Min Range: -4.8605
Max Act: 4.5480. Min Act: -0.1700
Data Index: 4642857 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8605. Min Range: -4.8605
Max Act: 4.5168. Min Act: -0.1700
Data Index: 3442856 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8605. Min Range: -4.8605
Max Act: 4.5168. Min Act: -0.1700
Data Index: 1545412 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8605. Min Range: -4.8605
Max Act: 4.5168. Min Act: -0.1700
Data Index: 1655045 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8605. Min Range: -4.8605
Max Act: 4.5168. Min Act: -0.1700
Data Index: 2693293 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19