Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3875 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8131. Min Range: -2.8131
Max Act: 2.8131. Min Act: -0.1700
Data Index: 8828443 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8131. Min Range: -2.8131
Max Act: 2.7014. Min Act: -0.1700
Data Index: 7521942 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8131. Min Range: -2.8131
Max Act: 2.6694. Min Act: -0.1700
Data Index: 1371014 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8131. Min Range: -2.8131
Max Act: 2.6373. Min Act: -0.1700
Data Index: 7850554 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8131. Min Range: -2.8131
Max Act: 2.6052. Min Act: -0.1700
Data Index: 2414184 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8131. Min Range: -2.8131
Max Act: 2.5891. Min Act: -0.1700
Data Index: 6339556 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8131. Min Range: -2.8131
Max Act: 2.5891. Min Act: -0.1700
Data Index: 3517508 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8131. Min Range: -2.8131
Max Act: 2.5568. Min Act: -0.1700
Data Index: 6304369 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8131. Min Range: -2.8131
Max Act: 2.5407. Min Act: -0.1700
Data Index: 5263740 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8131. Min Range: -2.8131
Max Act: 2.5407. Min Act: -0.1700
Data Index: 3838121 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8131. Min Range: -2.8131
Max Act: 2.5083. Min Act: -0.1700
Data Index: 1284104 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8131. Min Range: -2.8131
Max Act: 2.5245. Min Act: -0.1700
Data Index: 3034532 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8131. Min Range: -2.8131
Max Act: 2.5245. Min Act: -0.1700
Data Index: 6068322 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8131. Min Range: -2.8131
Max Act: 2.5083. Min Act: -0.1700
Data Index: 80279 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8131. Min Range: -2.8131
Max Act: 2.5083. Min Act: -0.1700
Data Index: 8798561 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8131. Min Range: -2.8131
Max Act: 2.4921. Min Act: -0.1700
Data Index: 5841237 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8131. Min Range: -2.8131
Max Act: 2.5083. Min Act: -0.1700
Data Index: 8173242 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8131. Min Range: -2.8131
Max Act: 2.4921. Min Act: -0.1700
Data Index: 1502353 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8131. Min Range: -2.8131
Max Act: 2.4921. Min Act: -0.1700
Data Index: 6570026 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8131. Min Range: -2.8131
Max Act: 2.4921. Min Act: -0.1700
Data Index: 5474005 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19