Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1932 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2283. Min Range: -6.2283
Max Act: 6.2283. Min Act: -0.1700
Data Index: 2585997 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2283. Min Range: -6.2283
Max Act: 6.1033. Min Act: -0.1700
Data Index: 7012229 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2283. Min Range: -6.2283
Max Act: 6.0720. Min Act: -0.1700
Data Index: 8753732 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2283. Min Range: -6.2283
Max Act: 5.9783. Min Act: -0.1700
Data Index: 3041788 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2283. Min Range: -6.2283
Max Act: 5.9158. Min Act: -0.1700
Data Index: 3892027 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2283. Min Range: -6.2283
Max Act: 5.9158. Min Act: -0.1700
Data Index: 6893306 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2283. Min Range: -6.2283
Max Act: 5.9158. Min Act: -0.1700
Data Index: 4867405 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2283. Min Range: -6.2283
Max Act: 5.8845. Min Act: -0.1700
Data Index: 242391 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2283. Min Range: -6.2283
Max Act: 5.9158. Min Act: -0.1700
Data Index: 216769 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2283. Min Range: -6.2283
Max Act: 5.9158. Min Act: -0.1700
Data Index: 5395812 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2283. Min Range: -6.2283
Max Act: 5.8845. Min Act: -0.1700
Data Index: 8811644 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2283. Min Range: -6.2283
Max Act: 5.8220. Min Act: -0.1700
Data Index: 3051483 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2283. Min Range: -6.2283
Max Act: 5.7908. Min Act: -0.1700
Data Index: 4016754 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2283. Min Range: -6.2283
Max Act: 5.7908. Min Act: -0.1700
Data Index: 5704571 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2283. Min Range: -6.2283
Max Act: 5.8533. Min Act: -0.1700
Data Index: 995173 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2283. Min Range: -6.2283
Max Act: 5.8220. Min Act: -0.1700
Data Index: 4266797 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2283. Min Range: -6.2283
Max Act: 5.7908. Min Act: -0.1700
Data Index: 5188469 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2283. Min Range: -6.2283
Max Act: 5.7595. Min Act: -0.1700
Data Index: 946134 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2283. Min Range: -6.2283
Max Act: 5.7595. Min Act: -0.1700
Data Index: 5056506 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2283. Min Range: -6.2283
Max Act: 5.7595. Min Act: -0.1700
Data Index: 1951588 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19