Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2406 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.1784. Min Range: -13.1784
Max Act: 13.1784. Min Act: -0.1700
Data Index: 5063281 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.1784. Min Range: -13.1784
Max Act: 13.0534. Min Act: -0.1700
Data Index: 2199102 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.1784. Min Range: -13.1784
Max Act: 13.0534. Min Act: -0.1700
Data Index: 8400716 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.1784. Min Range: -13.1784
Max Act: 13.0534. Min Act: -0.1700
Data Index: 5856284 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.1784. Min Range: -13.1784
Max Act: 12.8659. Min Act: -0.1700
Data Index: 7958482 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.1784. Min Range: -13.1784
Max Act: 12.8034. Min Act: -0.1700
Data Index: 7586351 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.1784. Min Range: -13.1784
Max Act: 12.7409. Min Act: -0.1700
Data Index: 6964112 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.1784. Min Range: -13.1784
Max Act: 12.7409. Min Act: -0.1700
Data Index: 47420 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.1784. Min Range: -13.1784
Max Act: 12.7409. Min Act: -0.1700
Data Index: 5785935 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.1784. Min Range: -13.1784
Max Act: 12.6784. Min Act: -0.1700
Data Index: 3280149 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.1784. Min Range: -13.1784
Max Act: 12.6784. Min Act: -0.1700
Data Index: 7532504 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.1784. Min Range: -13.1784
Max Act: 12.6159. Min Act: -0.1700
Data Index: 1865647 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.1784. Min Range: -13.1784
Max Act: 12.6159. Min Act: -0.1700
Data Index: 1897989 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.1784. Min Range: -13.1784
Max Act: 12.5534. Min Act: -0.1700
Data Index: 1813039 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.1784. Min Range: -13.1784
Max Act: 12.6159. Min Act: -0.1700
Data Index: 4517322 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.1784. Min Range: -13.1784
Max Act: 12.4909. Min Act: -0.1700
Data Index: 204348 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.1784. Min Range: -13.1784
Max Act: 12.5534. Min Act: -0.1700
Data Index: 4236329 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.1784. Min Range: -13.1784
Max Act: 12.4909. Min Act: -0.1700
Data Index: 5509529 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.1784. Min Range: -13.1784
Max Act: 12.4909. Min Act: -0.1700
Data Index: 6172854 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.1784. Min Range: -13.1784
Max Act: 12.4284. Min Act: -0.1700
Data Index: 1847392 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19