Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 2665 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.3398. Min Range: -1.3398
Max Act: 1.3398. Min Act: -0.0001
Data Index: 408542 (The Pile)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3398. Min Range: -1.3398
Max Act: 1.1839. Min Act: -0.0001
Data Index: 499306 (The Pile)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3398. Min Range: -1.3398
Max Act: 1.2413. Min Act: -0.0001
Data Index: 324620 (The Pile)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3398. Min Range: -1.3398
Max Act: 1.1190. Min Act: -0.0001
Data Index: 690109 (The Pile)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3398. Min Range: -1.3398
Max Act: 1.0644. Min Act: -0.0001
Data Index: 1935838 (The Pile)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3398. Min Range: -1.3398
Max Act: 1.0090. Min Act: -0.0001
Data Index: 524045 (The Pile)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3398. Min Range: -1.3398
Max Act: 0.9846. Min Act: -0.0001
Data Index: 1358520 (The Pile)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3398. Min Range: -1.3398
Max Act: 0.9895. Min Act: -0.0001
Data Index: 1608978 (The Pile)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3398. Min Range: -1.3398
Max Act: 0.8873. Min Act: -0.0001
Data Index: 1111241 (The Pile)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3398. Min Range: -1.3398
Max Act: 0.9888. Min Act: -0.0001
Data Index: 1672405 (The Pile)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3398. Min Range: -1.3398
Max Act: 0.9002. Min Act: -0.0001
Data Index: 1079874 (The Pile)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3398. Min Range: -1.3398
Max Act: 0.9811. Min Act: -0.0001
Data Index: 1535216 (The Pile)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3398. Min Range: -1.3398
Max Act: 0.8712. Min Act: -0.0001
Data Index: 1493462 (The Pile)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3398. Min Range: -1.3398
Max Act: 0.9332. Min Act: -0.0001
Data Index: 876739 (The Pile)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3398. Min Range: -1.3398
Max Act: 0.9543. Min Act: -0.0001
Data Index: 414084 (The Pile)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3398. Min Range: -1.3398
Max Act: 0.9353. Min Act: -0.0001
Data Index: 893533 (The Pile)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3398. Min Range: -1.3398
Max Act: 0.8859. Min Act: -0.0001
Data Index: 1004183 (The Pile)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3398. Min Range: -1.3398
Max Act: 0.8342. Min Act: -0.0001
Data Index: 74758 (The Pile)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3398. Min Range: -1.3398
Max Act: 0.8013. Min Act: -0.0001
Data Index: 1420889 (The Pile)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3398. Min Range: -1.3398
Max Act: 0.8757. Min Act: -0.0001
Data Index: 1594281 (The Pile)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19