Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2868 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2383. Min Range: -4.2383
Max Act: 4.2383. Min Act: -0.1700
Data Index: 5070694 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2383. Min Range: -4.2383
Max Act: 4.0352. Min Act: -0.1700
Data Index: 5159585 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2383. Min Range: -4.2383
Max Act: 4.0821. Min Act: -0.1700
Data Index: 8699872 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2383. Min Range: -4.2383
Max Act: 4.0352. Min Act: -0.1700
Data Index: 7805925 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2383. Min Range: -4.2383
Max Act: 3.9101. Min Act: -0.1700
Data Index: 800425 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2383. Min Range: -4.2383
Max Act: 3.9258. Min Act: -0.1700
Data Index: 8304263 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2383. Min Range: -4.2383
Max Act: 3.9570. Min Act: -0.1700
Data Index: 4651986 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2383. Min Range: -4.2383
Max Act: 3.9414. Min Act: -0.1700
Data Index: 2621683 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2383. Min Range: -4.2383
Max Act: 3.9101. Min Act: -0.1700
Data Index: 6882002 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2383. Min Range: -4.2383
Max Act: 3.9414. Min Act: -0.1700
Data Index: 6346782 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2383. Min Range: -4.2383
Max Act: 3.8632. Min Act: -0.1700
Data Index: 5761486 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2383. Min Range: -4.2383
Max Act: 3.9101. Min Act: -0.1700
Data Index: 2914499 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2383. Min Range: -4.2383
Max Act: 3.8320. Min Act: -0.1700
Data Index: 938158 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2383. Min Range: -4.2383
Max Act: 3.8163. Min Act: -0.1700
Data Index: 114377 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2383. Min Range: -4.2383
Max Act: 3.8163. Min Act: -0.1700
Data Index: 6864775 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2383. Min Range: -4.2383
Max Act: 3.8320. Min Act: -0.1700
Data Index: 474691 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2383. Min Range: -4.2383
Max Act: 3.8320. Min Act: -0.1700
Data Index: 4205336 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2383. Min Range: -4.2383
Max Act: 3.8163. Min Act: -0.1700
Data Index: 88090 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2383. Min Range: -4.2383
Max Act: 3.8163. Min Act: -0.1700
Data Index: 3901441 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2383. Min Range: -4.2383
Max Act: 3.8007. Min Act: -0.1700
Data Index: 1951953 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19