Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 2612 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 0.4563. Min Range: -0.4563
Max Act: 0.4563. Min Act: -0.0002
Data Index: 709905 (The Pile)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4563. Min Range: -0.4563
Max Act: 0.4445. Min Act: -0.0002
Data Index: 1961862 (The Pile)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4563. Min Range: -0.4563
Max Act: 0.3741. Min Act: -0.0002
Data Index: 1554850 (The Pile)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4563. Min Range: -0.4563
Max Act: 0.3862. Min Act: -0.0002
Data Index: 63305 (The Pile)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4563. Min Range: -0.4563
Max Act: 0.3377. Min Act: -0.0002
Data Index: 1106985 (The Pile)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4563. Min Range: -0.4563
Max Act: 0.3325. Min Act: -0.0002
Data Index: 1327163 (The Pile)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4563. Min Range: -0.4563
Max Act: 0.3627. Min Act: -0.0002
Data Index: 1844012 (The Pile)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4563. Min Range: -0.4563
Max Act: 0.3834. Min Act: -0.0002
Data Index: 240316 (The Pile)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4563. Min Range: -0.4563
Max Act: 0.3829. Min Act: -0.0002
Data Index: 293251 (The Pile)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4563. Min Range: -0.4563
Max Act: 0.3516. Min Act: -0.0002
Data Index: 383540 (The Pile)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4563. Min Range: -0.4563
Max Act: 0.3452. Min Act: -0.0002
Data Index: 189218 (The Pile)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4563. Min Range: -0.4563
Max Act: 0.3784. Min Act: -0.0002
Data Index: 1368868 (The Pile)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4563. Min Range: -0.4563
Max Act: 0.3544. Min Act: -0.0002
Data Index: 1152210 (The Pile)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4563. Min Range: -0.4563
Max Act: 0.3745. Min Act: -0.0002
Data Index: 1807813 (The Pile)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4563. Min Range: -0.4563
Max Act: 0.3524. Min Act: -0.0002
Data Index: 882081 (The Pile)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4563. Min Range: -0.4563
Max Act: 0.3183. Min Act: -0.0002
Data Index: 88347 (The Pile)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4563. Min Range: -0.4563
Max Act: 0.3388. Min Act: -0.0002
Data Index: 283544 (The Pile)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4563. Min Range: -0.4563
Max Act: 0.3365. Min Act: -0.0002
Data Index: 161328 (The Pile)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4563. Min Range: -0.4563
Max Act: 0.3723. Min Act: -0.0002
Data Index: 326172 (The Pile)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4563. Min Range: -0.4563
Max Act: 0.3150. Min Act: -0.0002
Data Index: 344226 (The Pile)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19