Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2475 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3821. Min Range: -3.3821
Max Act: 3.3821. Min Act: -0.1700
Data Index: 1653821 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3821. Min Range: -3.3821
Max Act: 3.3507. Min Act: -0.1700
Data Index: 1394324 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3821. Min Range: -3.3821
Max Act: 3.3507. Min Act: -0.1700
Data Index: 1164571 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3821. Min Range: -3.3821
Max Act: 3.3037. Min Act: -0.1700
Data Index: 6246176 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3821. Min Range: -3.3821
Max Act: 3.2880. Min Act: -0.1700
Data Index: 3599144 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3821. Min Range: -3.3821
Max Act: 3.3037. Min Act: -0.1700
Data Index: 363375 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3821. Min Range: -3.3821
Max Act: 3.2566. Min Act: -0.1700
Data Index: 8152587 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3821. Min Range: -3.3821
Max Act: 3.2723. Min Act: -0.1700
Data Index: 7755828 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3821. Min Range: -3.3821
Max Act: 3.2408. Min Act: -0.1700
Data Index: 3420155 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3821. Min Range: -3.3821
Max Act: 3.2566. Min Act: -0.1700
Data Index: 7182974 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3821. Min Range: -3.3821
Max Act: 3.2408. Min Act: -0.1700
Data Index: 6830575 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3821. Min Range: -3.3821
Max Act: 3.2408. Min Act: -0.1700
Data Index: 1242794 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3821. Min Range: -3.3821
Max Act: 3.2408. Min Act: -0.1700
Data Index: 5951314 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3821. Min Range: -3.3821
Max Act: 3.2094. Min Act: -0.1700
Data Index: 5525488 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3821. Min Range: -3.3821
Max Act: 3.2251. Min Act: -0.1700
Data Index: 2777117 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3821. Min Range: -3.3821
Max Act: 3.2094. Min Act: -0.1700
Data Index: 3238644 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3821. Min Range: -3.3821
Max Act: 3.1937. Min Act: -0.1700
Data Index: 965707 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3821. Min Range: -3.3821
Max Act: 3.2094. Min Act: -0.1700
Data Index: 7053082 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3821. Min Range: -3.3821
Max Act: 3.1779. Min Act: -0.1700
Data Index: 1182108 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3821. Min Range: -3.3821
Max Act: 3.2094. Min Act: -0.1700
Data Index: 473209 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #19