Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1183 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.8678. Min Range: -0.8678
Max Act: 0.8678. Min Act: -0.0000
Data Index: 934379 (The Pile)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8678. Min Range: -0.8678
Max Act: 0.8533. Min Act: -0.0000
Data Index: 584149 (The Pile)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8678. Min Range: -0.8678
Max Act: 0.7882. Min Act: -0.0000
Data Index: 1667624 (The Pile)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8678. Min Range: -0.8678
Max Act: 0.7068. Min Act: -0.0000
Data Index: 944959 (The Pile)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8678. Min Range: -0.8678
Max Act: 0.7817. Min Act: 0.0000
Data Index: 1675929 (The Pile)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8678. Min Range: -0.8678
Max Act: 0.6458. Min Act: -0.0000
Data Index: 667397 (The Pile)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8678. Min Range: -0.8678
Max Act: 0.6684. Min Act: -0.0000
Data Index: 990580 (The Pile)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8678. Min Range: -0.8678
Max Act: 0.7226. Min Act: -0.0000
Data Index: 1977003 (The Pile)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8678. Min Range: -0.8678
Max Act: 0.6368. Min Act: -0.0000
Data Index: 1929182 (The Pile)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8678. Min Range: -0.8678
Max Act: 0.5751. Min Act: -0.0000
Data Index: 1663928 (The Pile)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8678. Min Range: -0.8678
Max Act: 0.6077. Min Act: -0.0000
Data Index: 565655 (The Pile)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8678. Min Range: -0.8678
Max Act: 0.6028. Min Act: -0.0000
Data Index: 1528884 (The Pile)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8678. Min Range: -0.8678
Max Act: 0.6774. Min Act: -0.0000
Data Index: 182828 (The Pile)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8678. Min Range: -0.8678
Max Act: 0.5970. Min Act: -0.0000
Data Index: 569791 (The Pile)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8678. Min Range: -0.8678
Max Act: 0.5657. Min Act: -0.0000
Data Index: 973813 (The Pile)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8678. Min Range: -0.8678
Max Act: 0.5689. Min Act: -0.0000
Data Index: 279088 (The Pile)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8678. Min Range: -0.8678
Max Act: 0.5909. Min Act: -0.0000
Data Index: 14287 (The Pile)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8678. Min Range: -0.8678
Max Act: 0.6102. Min Act: -0.0000
Data Index: 1650540 (The Pile)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8678. Min Range: -0.8678
Max Act: 0.6040. Min Act: 0.0000
Data Index: 23586 (The Pile)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8678. Min Range: -0.8678
Max Act: 0.6329. Min Act: -0.0000
Data Index: 369829 (The Pile)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19