Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3496 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6032. Min Range: -6.6032
Max Act: 6.6032. Min Act: -0.1700
Data Index: 6344401 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6032. Min Range: -6.6032
Max Act: 6.5094. Min Act: -0.1700
Data Index: 400520 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6032. Min Range: -6.6032
Max Act: 6.3532. Min Act: -0.1700
Data Index: 2176137 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6032. Min Range: -6.6032
Max Act: 6.3532. Min Act: -0.1700
Data Index: 5148626 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6032. Min Range: -6.6032
Max Act: 6.3219. Min Act: -0.1700
Data Index: 6384090 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6032. Min Range: -6.6032
Max Act: 6.3219. Min Act: -0.1700
Data Index: 4628479 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6032. Min Range: -6.6032
Max Act: 6.2594. Min Act: -0.1700
Data Index: 1800892 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6032. Min Range: -6.6032
Max Act: 6.1969. Min Act: -0.1700
Data Index: 5954665 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6032. Min Range: -6.6032
Max Act: 6.1969. Min Act: -0.1700
Data Index: 398716 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6032. Min Range: -6.6032
Max Act: 6.1344. Min Act: -0.1700
Data Index: 2899636 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6032. Min Range: -6.6032
Max Act: 6.1344. Min Act: -0.1700
Data Index: 2526091 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6032. Min Range: -6.6032
Max Act: 6.1032. Min Act: -0.1700
Data Index: 8190593 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6032. Min Range: -6.6032
Max Act: 6.1032. Min Act: -0.1700
Data Index: 3311578 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6032. Min Range: -6.6032
Max Act: 6.1032. Min Act: -0.1700
Data Index: 2221964 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6032. Min Range: -6.6032
Max Act: 6.0719. Min Act: -0.1700
Data Index: 4916632 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6032. Min Range: -6.6032
Max Act: 6.0407. Min Act: -0.1700
Data Index: 8477889 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6032. Min Range: -6.6032
Max Act: 6.0094. Min Act: -0.1700
Data Index: 7462361 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6032. Min Range: -6.6032
Max Act: 6.0094. Min Act: -0.1700
Data Index: 8087108 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6032. Min Range: -6.6032
Max Act: 6.0094. Min Act: -0.1700
Data Index: 1099172 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6032. Min Range: -6.6032
Max Act: 6.0094. Min Act: -0.1700
Data Index: 7065577 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19