Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2937 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8256. Min Range: -6.8256
Max Act: 6.8256. Min Act: -0.1700
Data Index: 2588776 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8256. Min Range: -6.8256
Max Act: 6.7319. Min Act: -0.1700
Data Index: 2588775 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8256. Min Range: -6.8256
Max Act: 6.6694. Min Act: -0.1700
Data Index: 8015333 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8256. Min Range: -6.8256
Max Act: 6.6694. Min Act: -0.1700
Data Index: 3481542 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8256. Min Range: -6.8256
Max Act: 6.5756. Min Act: -0.1700
Data Index: 1668081 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8256. Min Range: -6.8256
Max Act: 6.5756. Min Act: -0.1700
Data Index: 6190476 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8256. Min Range: -6.8256
Max Act: 6.5444. Min Act: -0.1700
Data Index: 4409565 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8256. Min Range: -6.8256
Max Act: 6.5131. Min Act: -0.1700
Data Index: 4828537 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8256. Min Range: -6.8256
Max Act: 6.5131. Min Act: -0.1700
Data Index: 997568 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8256. Min Range: -6.8256
Max Act: 6.5131. Min Act: -0.1700
Data Index: 5210439 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8256. Min Range: -6.8256
Max Act: 6.4819. Min Act: -0.1700
Data Index: 6282069 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8256. Min Range: -6.8256
Max Act: 6.4819. Min Act: -0.1700
Data Index: 1416991 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8256. Min Range: -6.8256
Max Act: 6.4819. Min Act: -0.1700
Data Index: 3109626 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8256. Min Range: -6.8256
Max Act: 6.4819. Min Act: -0.1700
Data Index: 4519776 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8256. Min Range: -6.8256
Max Act: 6.4506. Min Act: -0.1700
Data Index: 4196175 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8256. Min Range: -6.8256
Max Act: 6.4506. Min Act: -0.1700
Data Index: 6464953 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8256. Min Range: -6.8256
Max Act: 6.4506. Min Act: -0.1700
Data Index: 4470435 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8256. Min Range: -6.8256
Max Act: 6.4194. Min Act: -0.1700
Data Index: 6272578 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8256. Min Range: -6.8256
Max Act: 6.4194. Min Act: -0.1700
Data Index: 2580765 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8256. Min Range: -6.8256
Max Act: 6.3881. Min Act: -0.1700
Data Index: 8784700 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #19