Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 631 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.7757. Min Range: -1.7757
Max Act: 1.7484. Min Act: -0.0001
Data Index: 1032357 (The Pile)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7757. Min Range: -1.7757
Max Act: 1.7757. Min Act: -0.0001
Data Index: 1326534 (The Pile)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7757. Min Range: -1.7757
Max Act: 1.6415. Min Act: -0.0001
Data Index: 327370 (The Pile)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7757. Min Range: -1.7757
Max Act: 1.6653. Min Act: -0.0001
Data Index: 449747 (The Pile)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7757. Min Range: -1.7757
Max Act: 1.4880. Min Act: -0.0001
Data Index: 971273 (The Pile)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7757. Min Range: -1.7757
Max Act: 1.4430. Min Act: -0.0001
Data Index: 823686 (The Pile)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7757. Min Range: -1.7757
Max Act: 1.3296. Min Act: -0.0001
Data Index: 1368669 (The Pile)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7757. Min Range: -1.7757
Max Act: 1.4374. Min Act: -0.0001
Data Index: 100127 (The Pile)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7757. Min Range: -1.7757
Max Act: 1.3916. Min Act: -0.0001
Data Index: 303034 (The Pile)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7757. Min Range: -1.7757
Max Act: 1.4813. Min Act: -0.0001
Data Index: 384322 (The Pile)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7757. Min Range: -1.7757
Max Act: 1.3371. Min Act: -0.0001
Data Index: 1432906 (The Pile)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7757. Min Range: -1.7757
Max Act: 1.3543. Min Act: -0.0001
Data Index: 273608 (The Pile)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7757. Min Range: -1.7757
Max Act: 1.3929. Min Act: -0.0001
Data Index: 1763356 (The Pile)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7757. Min Range: -1.7757
Max Act: 1.3739. Min Act: -0.0001
Data Index: 1767356 (The Pile)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7757. Min Range: -1.7757
Max Act: 1.3337. Min Act: -0.0001
Data Index: 244056 (The Pile)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7757. Min Range: -1.7757
Max Act: 1.1315. Min Act: -0.0001
Data Index: 1718475 (The Pile)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7757. Min Range: -1.7757
Max Act: 1.2759. Min Act: -0.0001
Data Index: 1060682 (The Pile)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7757. Min Range: -1.7757
Max Act: 1.2280. Min Act: -0.0001
Data Index: 1609066 (The Pile)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7757. Min Range: -1.7757
Max Act: 1.3436. Min Act: -0.0001
Data Index: 996637 (The Pile)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7757. Min Range: -1.7757
Max Act: 1.2432. Min Act: -0.0001
Data Index: 679572 (The Pile)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19