Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2132 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.6343. Min Range: -2.6343
Max Act: 2.6343. Min Act: -0.0001
Data Index: 527085 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6343. Min Range: -2.6343
Max Act: 2.4329. Min Act: -0.0001
Data Index: 731056 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6343. Min Range: -2.6343
Max Act: 2.2653. Min Act: -0.0001
Data Index: 592648 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6343. Min Range: -2.6343
Max Act: 2.2365. Min Act: -0.0001
Data Index: 143397 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6343. Min Range: -2.6343
Max Act: 2.2441. Min Act: -0.0001
Data Index: 448476 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6343. Min Range: -2.6343
Max Act: 2.2309. Min Act: -0.0001
Data Index: 1020438 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6343. Min Range: -2.6343
Max Act: 2.3427. Min Act: -0.0001
Data Index: 317274 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6343. Min Range: -2.6343
Max Act: 2.1753. Min Act: -0.0001
Data Index: 1007309 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6343. Min Range: -2.6343
Max Act: 2.1417. Min Act: -0.0001
Data Index: 354920 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6343. Min Range: -2.6343
Max Act: 2.2484. Min Act: -0.0001
Data Index: 1210526 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6343. Min Range: -2.6343
Max Act: 2.0946. Min Act: -0.0001
Data Index: 1331666 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6343. Min Range: -2.6343
Max Act: 2.0765. Min Act: -0.0001
Data Index: 506581 (C4 (Web Text))
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6343. Min Range: -2.6343
Max Act: 1.9613. Min Act: -0.0001
Data Index: 187663 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6343. Min Range: -2.6343
Max Act: 1.9787. Min Act: -0.0001
Data Index: 1294124 (C4 (Web Text))
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6343. Min Range: -2.6343
Max Act: 2.0307. Min Act: -0.0001
Data Index: 654170 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6343. Min Range: -2.6343
Max Act: 2.0240. Min Act: -0.0001
Data Index: 576202 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6343. Min Range: -2.6343
Max Act: 1.9090. Min Act: -0.0001
Data Index: 1338631 (C4 (Web Text))
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6343. Min Range: -2.6343
Max Act: 2.0159. Min Act: -0.0001
Data Index: 609341 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6343. Min Range: -2.6343
Max Act: 1.9145. Min Act: -0.0001
Data Index: 502214 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6343. Min Range: -2.6343
Max Act: 1.7787. Min Act: -0.0001
Data Index: 8099 (C4 (Web Text))
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19