Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 109 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7098. Min Range: -3.7098
Max Act: 3.7098. Min Act: -0.1700
Data Index: 4112625 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7098. Min Range: -3.7098
Max Act: 3.5690. Min Act: -0.1700
Data Index: 2511749 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7098. Min Range: -3.7098
Max Act: 3.5064. Min Act: -0.1700
Data Index: 8513853 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7098. Min Range: -3.7098
Max Act: 3.4907. Min Act: -0.1700
Data Index: 1579200 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7098. Min Range: -3.7098
Max Act: 3.4750. Min Act: -0.1700
Data Index: 1004327 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7098. Min Range: -3.7098
Max Act: 3.4594. Min Act: -0.1700
Data Index: 8044311 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7098. Min Range: -3.7098
Max Act: 3.4437. Min Act: -0.1700
Data Index: 8428043 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7098. Min Range: -3.7098
Max Act: 3.4124. Min Act: -0.1700
Data Index: 8604812 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7098. Min Range: -3.7098
Max Act: 3.4124. Min Act: -0.1700
Data Index: 484903 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7098. Min Range: -3.7098
Max Act: 3.3967. Min Act: -0.1700
Data Index: 442457 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7098. Min Range: -3.7098
Max Act: 3.3653. Min Act: -0.1700
Data Index: 5550485 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7098. Min Range: -3.7098
Max Act: 3.3967. Min Act: -0.1700
Data Index: 705332 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7098. Min Range: -3.7098
Max Act: 3.3653. Min Act: -0.1700
Data Index: 3576541 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7098. Min Range: -3.7098
Max Act: 3.3653. Min Act: -0.1700
Data Index: 4132804 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7098. Min Range: -3.7098
Max Act: 3.3810. Min Act: -0.1700
Data Index: 7090834 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7098. Min Range: -3.7098
Max Act: 3.3496. Min Act: -0.1700
Data Index: 684118 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7098. Min Range: -3.7098
Max Act: 3.3496. Min Act: -0.1700
Data Index: 6977986 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7098. Min Range: -3.7098
Max Act: 3.3182. Min Act: -0.1700
Data Index: 7125727 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7098. Min Range: -3.7098
Max Act: 3.3496. Min Act: -0.1700
Data Index: 1548316 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7098. Min Range: -3.7098
Max Act: 3.3025. Min Act: -0.1700
Data Index: 1738860 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #19