Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2925 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.1362. Min Range: -2.1362
Max Act: 2.1362. Min Act: -0.0001
Data Index: 245521 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1362. Min Range: -2.1362
Max Act: 1.8520. Min Act: -0.0001
Data Index: 456452 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1362. Min Range: -2.1362
Max Act: 1.7181. Min Act: -0.0001
Data Index: 292515 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1362. Min Range: -2.1362
Max Act: 1.8470. Min Act: -0.0001
Data Index: 140100 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1362. Min Range: -2.1362
Max Act: 1.6693. Min Act: -0.0001
Data Index: 966045 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1362. Min Range: -2.1362
Max Act: 1.6443. Min Act: -0.0001
Data Index: 779670 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1362. Min Range: -2.1362
Max Act: 1.4941. Min Act: -0.0001
Data Index: 695387 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1362. Min Range: -2.1362
Max Act: 1.5524. Min Act: -0.0001
Data Index: 916088 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1362. Min Range: -2.1362
Max Act: 1.4586. Min Act: -0.0001
Data Index: 20996 (C4 (Web Text))
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1362. Min Range: -2.1362
Max Act: 1.4603. Min Act: -0.0001
Data Index: 1267398 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1362. Min Range: -2.1362
Max Act: 1.5197. Min Act: -0.0001
Data Index: 527145 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1362. Min Range: -2.1362
Max Act: 1.2731. Min Act: -0.0001
Data Index: 453537 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1362. Min Range: -2.1362
Max Act: 1.5426. Min Act: -0.0001
Data Index: 137764 (C4 (Web Text))
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1362. Min Range: -2.1362
Max Act: 1.6164. Min Act: -0.0001
Data Index: 1567135 (Python Code)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1362. Min Range: -2.1362
Max Act: 1.4290. Min Act: -0.0001
Data Index: 1003668 (C4 (Web Text))
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1362. Min Range: -2.1362
Max Act: 1.4180. Min Act: -0.0001
Data Index: 72640 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1362. Min Range: -2.1362
Max Act: 1.3314. Min Act: -0.0001
Data Index: 1216426 (C4 (Web Text))
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1362. Min Range: -2.1362
Max Act: 1.4635. Min Act: -0.0001
Data Index: 1125833 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1362. Min Range: -2.1362
Max Act: 1.4694. Min Act: -0.0001
Data Index: 366671 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1362. Min Range: -2.1362
Max Act: 1.5356. Min Act: -0.0001
Data Index: 9536 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19