Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 784 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9864. Min Range: -6.9864
Max Act: 6.9864. Min Act: -0.1700
Data Index: 2740046 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9864. Min Range: -6.9864
Max Act: 6.8927. Min Act: -0.1700
Data Index: 5801060 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9864. Min Range: -6.9864
Max Act: 6.3302. Min Act: -0.1700
Data Index: 8140386 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9864. Min Range: -6.9864
Max Act: 6.2364. Min Act: -0.1700
Data Index: 3716071 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9864. Min Range: -6.9864
Max Act: 6.2052. Min Act: -0.1700
Data Index: 1642338 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9864. Min Range: -6.9864
Max Act: 6.1739. Min Act: -0.1700
Data Index: 6857773 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9864. Min Range: -6.9864
Max Act: 6.1114. Min Act: -0.1700
Data Index: 4249520 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9864. Min Range: -6.9864
Max Act: 6.1114. Min Act: -0.1700
Data Index: 3972567 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9864. Min Range: -6.9864
Max Act: 6.0489. Min Act: -0.1700
Data Index: 275580 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9864. Min Range: -6.9864
Max Act: 6.0177. Min Act: -0.1700
Data Index: 7425799 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9864. Min Range: -6.9864
Max Act: 6.0489. Min Act: -0.1700
Data Index: 4260259 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9864. Min Range: -6.9864
Max Act: 5.9864. Min Act: -0.1700
Data Index: 8561403 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9864. Min Range: -6.9864
Max Act: 5.9864. Min Act: -0.1700
Data Index: 3669100 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9864. Min Range: -6.9864
Max Act: 5.9864. Min Act: -0.1700
Data Index: 2553317 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9864. Min Range: -6.9864
Max Act: 5.9239. Min Act: -0.1700
Data Index: 8788298 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9864. Min Range: -6.9864
Max Act: 5.9552. Min Act: -0.1700
Data Index: 890434 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9864. Min Range: -6.9864
Max Act: 5.9239. Min Act: -0.1700
Data Index: 1496734 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9864. Min Range: -6.9864
Max Act: 5.9239. Min Act: -0.1700
Data Index: 5693773 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9864. Min Range: -6.9864
Max Act: 5.9552. Min Act: -0.1700
Data Index: 3035405 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9864. Min Range: -6.9864
Max Act: 5.9864. Min Act: -0.1700
Data Index: 4501391 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19