Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 3504 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.2266. Min Range: -1.2266
Max Act: 1.2266. Min Act: -0.0000
Data Index: 770555 (The Pile)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2266. Min Range: -1.2266
Max Act: 1.0177. Min Act: -0.0000
Data Index: 145095 (The Pile)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2266. Min Range: -1.2266
Max Act: 0.9143. Min Act: -0.0000
Data Index: 1832474 (The Pile)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2266. Min Range: -1.2266
Max Act: 0.8888. Min Act: -0.0000
Data Index: 513065 (The Pile)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2266. Min Range: -1.2266
Max Act: 0.9023. Min Act: -0.0000
Data Index: 789638 (The Pile)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2266. Min Range: -1.2266
Max Act: 0.8667. Min Act: -0.0000
Data Index: 1422949 (The Pile)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2266. Min Range: -1.2266
Max Act: 0.8648. Min Act: -0.0000
Data Index: 236449 (The Pile)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2266. Min Range: -1.2266
Max Act: 0.8344. Min Act: -0.0000
Data Index: 4389 (The Pile)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2266. Min Range: -1.2266
Max Act: 0.8808. Min Act: -0.0000
Data Index: 45826 (The Pile)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2266. Min Range: -1.2266
Max Act: 0.8170. Min Act: -0.0000
Data Index: 47071 (The Pile)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2266. Min Range: -1.2266
Max Act: 0.8450. Min Act: -0.0000
Data Index: 1502057 (The Pile)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2266. Min Range: -1.2266
Max Act: 0.8164. Min Act: -0.0000
Data Index: 1078615 (The Pile)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2266. Min Range: -1.2266
Max Act: 0.8431. Min Act: -0.0000
Data Index: 283183 (The Pile)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2266. Min Range: -1.2266
Max Act: 0.8411. Min Act: -0.0000
Data Index: 1771674 (The Pile)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2266. Min Range: -1.2266
Max Act: 0.8375. Min Act: -0.0000
Data Index: 1211607 (The Pile)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2266. Min Range: -1.2266
Max Act: 0.8124. Min Act: -0.0000
Data Index: 840491 (The Pile)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2266. Min Range: -1.2266
Max Act: 0.8030. Min Act: -0.0000
Data Index: 875147 (The Pile)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2266. Min Range: -1.2266
Max Act: 0.8508. Min Act: -0.0000
Data Index: 1132758 (The Pile)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2266. Min Range: -1.2266
Max Act: 0.7924. Min Act: -0.0000
Data Index: 429183 (The Pile)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2266. Min Range: -1.2266
Max Act: 0.8074. Min Act: -0.0000
Data Index: 212643 (The Pile)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19