Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 64 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0674. Min Range: -6.0674
Max Act: 6.0674. Min Act: -0.1700
Data Index: 2662156 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0674. Min Range: -6.0674
Max Act: 6.0674. Min Act: -0.1700
Data Index: 7696497 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0674. Min Range: -6.0674
Max Act: 5.9112. Min Act: -0.1700
Data Index: 3495225 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0674. Min Range: -6.0674
Max Act: 5.8174. Min Act: -0.1700
Data Index: 2191894 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0674. Min Range: -6.0674
Max Act: 5.8487. Min Act: -0.1700
Data Index: 1942641 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0674. Min Range: -6.0674
Max Act: 5.8487. Min Act: -0.1700
Data Index: 1445239 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0674. Min Range: -6.0674
Max Act: 5.8174. Min Act: -0.1700
Data Index: 6883792 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0674. Min Range: -6.0674
Max Act: 5.7862. Min Act: -0.1700
Data Index: 4657190 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0674. Min Range: -6.0674
Max Act: 5.7862. Min Act: -0.1700
Data Index: 7456194 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0674. Min Range: -6.0674
Max Act: 5.7862. Min Act: -0.1700
Data Index: 3710664 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0674. Min Range: -6.0674
Max Act: 5.7549. Min Act: -0.1700
Data Index: 8579714 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0674. Min Range: -6.0674
Max Act: 5.7237. Min Act: -0.1700
Data Index: 138287 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0674. Min Range: -6.0674
Max Act: 5.7237. Min Act: -0.1700
Data Index: 6542020 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0674. Min Range: -6.0674
Max Act: 5.7237. Min Act: -0.1700
Data Index: 2068088 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0674. Min Range: -6.0674
Max Act: 5.6924. Min Act: -0.1700
Data Index: 5078024 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0674. Min Range: -6.0674
Max Act: 5.6924. Min Act: -0.1700
Data Index: 4197005 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0674. Min Range: -6.0674
Max Act: 5.6612. Min Act: -0.1700
Data Index: 3283388 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0674. Min Range: -6.0674
Max Act: 5.6924. Min Act: -0.1700
Data Index: 4618971 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0674. Min Range: -6.0674
Max Act: 5.6299. Min Act: -0.1700
Data Index: 966702 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0674. Min Range: -6.0674
Max Act: 5.6924. Min Act: -0.1700
Data Index: 3707424 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #19