Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2384 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.9262. Min Range: -9.9262
Max Act: 9.8637. Min Act: -0.1700
Data Index: 4100661 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9262. Min Range: -9.9262
Max Act: 9.9262. Min Act: -0.1700
Data Index: 7800705 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9262. Min Range: -9.9262
Max Act: 9.8637. Min Act: -0.1700
Data Index: 7964229 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9262. Min Range: -9.9262
Max Act: 9.6762. Min Act: -0.1700
Data Index: 3302930 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9262. Min Range: -9.9262
Max Act: 9.7387. Min Act: -0.1700
Data Index: 3730620 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9262. Min Range: -9.9262
Max Act: 9.6762. Min Act: -0.1700
Data Index: 752333 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9262. Min Range: -9.9262
Max Act: 9.6762. Min Act: -0.1700
Data Index: 3730621 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9262. Min Range: -9.9262
Max Act: 9.6137. Min Act: -0.1700
Data Index: 322492 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9262. Min Range: -9.9262
Max Act: 9.6137. Min Act: -0.1700
Data Index: 7653449 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9262. Min Range: -9.9262
Max Act: 9.5512. Min Act: -0.1700
Data Index: 2522896 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9262. Min Range: -9.9262
Max Act: 9.5512. Min Act: -0.1700
Data Index: 5874129 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9262. Min Range: -9.9262
Max Act: 9.4887. Min Act: -0.1700
Data Index: 205855 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9262. Min Range: -9.9262
Max Act: 9.4887. Min Act: -0.1700
Data Index: 6524876 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9262. Min Range: -9.9262
Max Act: 9.4887. Min Act: -0.1700
Data Index: 4899022 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9262. Min Range: -9.9262
Max Act: 9.4262. Min Act: -0.1700
Data Index: 7438156 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9262. Min Range: -9.9262
Max Act: 9.4262. Min Act: -0.1700
Data Index: 5831289 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9262. Min Range: -9.9262
Max Act: 9.4887. Min Act: -0.1700
Data Index: 8372986 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9262. Min Range: -9.9262
Max Act: 9.3637. Min Act: -0.1700
Data Index: 3685806 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9262. Min Range: -9.9262
Max Act: 9.3637. Min Act: -0.1700
Data Index: 6122624 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9262. Min Range: -9.9262
Max Act: 9.3012. Min Act: -0.1700
Data Index: 473630 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19