Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 162 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0501. Min Range: -6.0501
Max Act: 6.0501. Min Act: -0.1700
Data Index: 2173040 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0501. Min Range: -6.0501
Max Act: 6.0501. Min Act: -0.1700
Data Index: 6921410 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0501. Min Range: -6.0501
Max Act: 5.9876. Min Act: -0.1700
Data Index: 777667 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0501. Min Range: -6.0501
Max Act: 5.9876. Min Act: -0.1700
Data Index: 5653278 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0501. Min Range: -6.0501
Max Act: 6.0188. Min Act: -0.1700
Data Index: 6350092 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0501. Min Range: -6.0501
Max Act: 5.9876. Min Act: -0.1700
Data Index: 3921686 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0501. Min Range: -6.0501
Max Act: 5.8626. Min Act: -0.1700
Data Index: 7423676 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0501. Min Range: -6.0501
Max Act: 5.8626. Min Act: -0.1700
Data Index: 5358558 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0501. Min Range: -6.0501
Max Act: 5.8938. Min Act: -0.1700
Data Index: 1164094 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0501. Min Range: -6.0501
Max Act: 5.8313. Min Act: -0.1700
Data Index: 3523977 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0501. Min Range: -6.0501
Max Act: 5.8313. Min Act: -0.1700
Data Index: 2999932 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0501. Min Range: -6.0501
Max Act: 5.8001. Min Act: -0.1700
Data Index: 43795 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0501. Min Range: -6.0501
Max Act: 5.8001. Min Act: -0.1700
Data Index: 973374 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0501. Min Range: -6.0501
Max Act: 5.7688. Min Act: -0.1700
Data Index: 5286923 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0501. Min Range: -6.0501
Max Act: 5.8001. Min Act: -0.1700
Data Index: 8044491 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0501. Min Range: -6.0501
Max Act: 5.7688. Min Act: -0.1700
Data Index: 3511216 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0501. Min Range: -6.0501
Max Act: 5.7688. Min Act: -0.1700
Data Index: 3980077 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0501. Min Range: -6.0501
Max Act: 5.7376. Min Act: -0.1700
Data Index: 3412056 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0501. Min Range: -6.0501
Max Act: 5.7376. Min Act: -0.1700
Data Index: 7460156 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0501. Min Range: -6.0501
Max Act: 5.7063. Min Act: -0.1700
Data Index: 7791301 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19