Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 22 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 3.8465. Min Range: -3.8465
Max Act: 3.8465. Min Act: -0.0001
Data Index: 1757039 (The Pile)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8465. Min Range: -3.8465
Max Act: 3.7252. Min Act: -0.0001
Data Index: 1397560 (The Pile)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8465. Min Range: -3.8465
Max Act: 3.7860. Min Act: -0.0001
Data Index: 1760114 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8465. Min Range: -3.8465
Max Act: 3.4179. Min Act: -0.0001
Data Index: 1174627 (The Pile)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8465. Min Range: -3.8465
Max Act: 3.6015. Min Act: -0.0001
Data Index: 1433237 (The Pile)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8465. Min Range: -3.8465
Max Act: 3.1707. Min Act: -0.0001
Data Index: 1187715 (The Pile)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8465. Min Range: -3.8465
Max Act: 3.0066. Min Act: -0.0001
Data Index: 1456290 (The Pile)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8465. Min Range: -3.8465
Max Act: 2.9685. Min Act: -0.0001
Data Index: 512711 (The Pile)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8465. Min Range: -3.8465
Max Act: 2.8397. Min Act: -0.0001
Data Index: 1460084 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8465. Min Range: -3.8465
Max Act: 2.8397. Min Act: -0.0001
Data Index: 1021749 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8465. Min Range: -3.8465
Max Act: 2.6954. Min Act: -0.0001
Data Index: 1318155 (The Pile)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8465. Min Range: -3.8465
Max Act: 2.6272. Min Act: -0.0001
Data Index: 1721266 (The Pile)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8465. Min Range: -3.8465
Max Act: 3.1150. Min Act: -0.0001
Data Index: 1098332 (The Pile)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8465. Min Range: -3.8465
Max Act: 2.8292. Min Act: -0.0001
Data Index: 188731 (The Pile)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8465. Min Range: -3.8465
Max Act: 3.2114. Min Act: -0.0001
Data Index: 1201963 (The Pile)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8465. Min Range: -3.8465
Max Act: 2.6862. Min Act: -0.0001
Data Index: 488312 (The Pile)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8465. Min Range: -3.8465
Max Act: 2.6745. Min Act: -0.0001
Data Index: 1164492 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8465. Min Range: -3.8465
Max Act: 2.7117. Min Act: -0.0001
Data Index: 498160 (The Pile)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8465. Min Range: -3.8465
Max Act: 2.6043. Min Act: -0.0001
Data Index: 1128929 (The Pile)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8465. Min Range: -3.8465
Max Act: 2.6542. Min Act: -0.0001
Data Index: 1060773 (The Pile)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19