Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4058 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7713. Min Range: -6.7713
Max Act: 6.7713. Min Act: -0.1700
Data Index: 6814623 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7713. Min Range: -6.7713
Max Act: 6.5838. Min Act: -0.1700
Data Index: 4667247 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7713. Min Range: -6.7713
Max Act: 6.5213. Min Act: -0.1700
Data Index: 6150063 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7713. Min Range: -6.7713
Max Act: 6.4588. Min Act: -0.1700
Data Index: 8458631 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7713. Min Range: -6.7713
Max Act: 6.4588. Min Act: -0.1700
Data Index: 8627498 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7713. Min Range: -6.7713
Max Act: 6.4276. Min Act: -0.1700
Data Index: 395467 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7713. Min Range: -6.7713
Max Act: 6.4588. Min Act: -0.1700
Data Index: 5294836 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7713. Min Range: -6.7713
Max Act: 6.4588. Min Act: -0.1700
Data Index: 8707626 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7713. Min Range: -6.7713
Max Act: 6.4276. Min Act: -0.1700
Data Index: 5660933 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7713. Min Range: -6.7713
Max Act: 6.3963. Min Act: -0.1700
Data Index: 5760300 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7713. Min Range: -6.7713
Max Act: 6.4276. Min Act: -0.1700
Data Index: 458649 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7713. Min Range: -6.7713
Max Act: 6.3963. Min Act: -0.1700
Data Index: 217328 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7713. Min Range: -6.7713
Max Act: 6.3963. Min Act: -0.1700
Data Index: 3666755 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7713. Min Range: -6.7713
Max Act: 6.3651. Min Act: -0.1700
Data Index: 1996315 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7713. Min Range: -6.7713
Max Act: 6.3651. Min Act: -0.1700
Data Index: 7104877 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7713. Min Range: -6.7713
Max Act: 6.3963. Min Act: -0.1700
Data Index: 2157961 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7713. Min Range: -6.7713
Max Act: 6.3963. Min Act: -0.1700
Data Index: 1917709 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7713. Min Range: -6.7713
Max Act: 6.3338. Min Act: -0.1700
Data Index: 7411341 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7713. Min Range: -6.7713
Max Act: 6.3338. Min Act: -0.1700
Data Index: 2833209 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7713. Min Range: -6.7713
Max Act: 6.3338. Min Act: -0.1700
Data Index: 5339207 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19