Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3269 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 6.7282. Min Range: -6.7282
Max Act: 6.7282. Min Act: -0.0001
Data Index: 1145357 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7282. Min Range: -6.7282
Max Act: 6.6071. Min Act: -0.0001
Data Index: 1091675 (C4 (Web Text))
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7282. Min Range: -6.7282
Max Act: 6.5511. Min Act: -0.0001
Data Index: 128774 (C4 (Web Text))
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7282. Min Range: -6.7282
Max Act: 6.3513. Min Act: -0.0001
Data Index: 1302568 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7282. Min Range: -6.7282
Max Act: 5.9188. Min Act: -0.0001
Data Index: 1489713 (Python Code)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7282. Min Range: -6.7282
Max Act: 5.9144. Min Act: -0.0001
Data Index: 643258 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7282. Min Range: -6.7282
Max Act: 6.0107. Min Act: -0.0001
Data Index: 1065479 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7282. Min Range: -6.7282
Max Act: 6.0188. Min Act: -0.0001
Data Index: 101471 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7282. Min Range: -6.7282
Max Act: 5.9547. Min Act: -0.0001
Data Index: 46154 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7282. Min Range: -6.7282
Max Act: 5.5417. Min Act: -0.0001
Data Index: 540481 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7282. Min Range: -6.7282
Max Act: 5.9158. Min Act: -0.0001
Data Index: 609302 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7282. Min Range: -6.7282
Max Act: 5.1743. Min Act: -0.0000
Data Index: 872982 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7282. Min Range: -6.7282
Max Act: 5.5158. Min Act: -0.0001
Data Index: 735621 (C4 (Web Text))
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7282. Min Range: -6.7282
Max Act: 6.0638. Min Act: -0.0001
Data Index: 786792 (C4 (Web Text))
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7282. Min Range: -6.7282
Max Act: 5.3443. Min Act: -0.0001
Data Index: 308222 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7282. Min Range: -6.7282
Max Act: 5.1867. Min Act: -0.0001
Data Index: 752311 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7282. Min Range: -6.7282
Max Act: 5.5373. Min Act: -0.0001
Data Index: 837381 (C4 (Web Text))
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7282. Min Range: -6.7282
Max Act: 5.4742. Min Act: -0.0001
Data Index: 921103 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7282. Min Range: -6.7282
Max Act: 5.2346. Min Act: -0.0001
Data Index: 555691 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7282. Min Range: -6.7282
Max Act: 5.2113. Min Act: -0.0001
Data Index: 897704 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19