Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3402 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5276. Min Range: -5.5276
Max Act: 5.5276. Min Act: -0.1700
Data Index: 7143956 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5276. Min Range: -5.5276
Max Act: 5.5276. Min Act: -0.1700
Data Index: 60464 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5276. Min Range: -5.5276
Max Act: 5.4651. Min Act: -0.1700
Data Index: 6739347 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5276. Min Range: -5.5276
Max Act: 5.4339. Min Act: -0.1700
Data Index: 142 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5276. Min Range: -5.5276
Max Act: 5.4339. Min Act: -0.1700
Data Index: 7741854 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5276. Min Range: -5.5276
Max Act: 5.3714. Min Act: -0.1700
Data Index: 7189159 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5276. Min Range: -5.5276
Max Act: 5.4026. Min Act: -0.1700
Data Index: 4784930 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5276. Min Range: -5.5276
Max Act: 5.4026. Min Act: -0.1700
Data Index: 4642507 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5276. Min Range: -5.5276
Max Act: 5.3714. Min Act: -0.1700
Data Index: 6406710 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5276. Min Range: -5.5276
Max Act: 5.3714. Min Act: -0.1700
Data Index: 2429047 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5276. Min Range: -5.5276
Max Act: 5.4026. Min Act: -0.1700
Data Index: 6645770 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5276. Min Range: -5.5276
Max Act: 5.3401. Min Act: -0.1700
Data Index: 7276410 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5276. Min Range: -5.5276
Max Act: 5.3401. Min Act: -0.1700
Data Index: 1599487 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5276. Min Range: -5.5276
Max Act: 5.3714. Min Act: -0.1700
Data Index: 5729085 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5276. Min Range: -5.5276
Max Act: 5.3714. Min Act: -0.1700
Data Index: 3237330 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5276. Min Range: -5.5276
Max Act: 5.3089. Min Act: -0.1700
Data Index: 3159938 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5276. Min Range: -5.5276
Max Act: 5.3089. Min Act: -0.1700
Data Index: 7914598 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5276. Min Range: -5.5276
Max Act: 5.3089. Min Act: -0.1700
Data Index: 1833703 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5276. Min Range: -5.5276
Max Act: 5.3401. Min Act: -0.1700
Data Index: 6257438 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5276. Min Range: -5.5276
Max Act: 5.2776. Min Act: -0.1700
Data Index: 5777561 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #19