Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1815 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.3438. Min Act: -0.1700
Data Index: 2331385 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.2813. Min Act: -0.1700
Data Index: 6968211 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.2501. Min Act: -0.1700
Data Index: 5719014 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.2188. Min Act: -0.1700
Data Index: 5847819 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.1876. Min Act: -0.1700
Data Index: 600344 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.1876. Min Act: -0.1700
Data Index: 7911185 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.1563. Min Act: -0.1700
Data Index: 2857149 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.1563. Min Act: -0.1700
Data Index: 4692500 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.1251. Min Act: -0.1700
Data Index: 405177 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.1251. Min Act: -0.1700
Data Index: 4799282 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.1251. Min Act: -0.1700
Data Index: 3825987 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.1563. Min Act: -0.1700
Data Index: 623762 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.1251. Min Act: -0.1700
Data Index: 4219556 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.1251. Min Act: -0.1700
Data Index: 5076580 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.0938. Min Act: -0.1700
Data Index: 7380188 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.0938. Min Act: -0.1700
Data Index: 1725926 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.0938. Min Act: -0.1700
Data Index: 36042 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.0626. Min Act: -0.1700
Data Index: 6582269 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.0938. Min Act: -0.1700
Data Index: 2942194 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.0626. Min Act: -0.1700
Data Index: 4376241 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19