Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3200 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9263. Min Range: -6.9263
Max Act: 6.9263. Min Act: -0.1700
Data Index: 910311 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9263. Min Range: -6.9263
Max Act: 6.9263. Min Act: -0.1700
Data Index: 2221397 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9263. Min Range: -6.9263
Max Act: 6.8638. Min Act: -0.1700
Data Index: 2408770 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9263. Min Range: -6.9263
Max Act: 6.7701. Min Act: -0.1700
Data Index: 7957845 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9263. Min Range: -6.9263
Max Act: 6.6763. Min Act: -0.1700
Data Index: 758410 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9263. Min Range: -6.9263
Max Act: 6.6763. Min Act: -0.1700
Data Index: 1050057 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9263. Min Range: -6.9263
Max Act: 6.5513. Min Act: -0.1700
Data Index: 7289157 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9263. Min Range: -6.9263
Max Act: 6.6138. Min Act: -0.1700
Data Index: 2487848 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9263. Min Range: -6.9263
Max Act: 6.5826. Min Act: -0.1700
Data Index: 4655141 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9263. Min Range: -6.9263
Max Act: 6.5826. Min Act: -0.1700
Data Index: 8445011 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9263. Min Range: -6.9263
Max Act: 6.5826. Min Act: -0.1700
Data Index: 1051804 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9263. Min Range: -6.9263
Max Act: 6.4888. Min Act: -0.1700
Data Index: 4173319 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9263. Min Range: -6.9263
Max Act: 6.5201. Min Act: -0.1700
Data Index: 6086752 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9263. Min Range: -6.9263
Max Act: 6.4576. Min Act: -0.1700
Data Index: 4005614 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9263. Min Range: -6.9263
Max Act: 6.5201. Min Act: -0.1700
Data Index: 8335167 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9263. Min Range: -6.9263
Max Act: 6.4263. Min Act: -0.1700
Data Index: 4278193 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9263. Min Range: -6.9263
Max Act: 6.4888. Min Act: -0.1700
Data Index: 3126688 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9263. Min Range: -6.9263
Max Act: 6.4263. Min Act: -0.1700
Data Index: 6198225 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9263. Min Range: -6.9263
Max Act: 6.4263. Min Act: -0.1700
Data Index: 8174131 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9263. Min Range: -6.9263
Max Act: 6.4263. Min Act: -0.1700
Data Index: 6994730 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19