Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2588 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 3.2792. Min Range: -3.2792
Max Act: 3.2792. Min Act: -0.0001
Data Index: 1030873 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2792. Min Range: -3.2792
Max Act: 3.1248. Min Act: -0.0001
Data Index: 206339 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2792. Min Range: -3.2792
Max Act: 3.1182. Min Act: -0.0001
Data Index: 1076733 (C4 (Web Text))
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2792. Min Range: -3.2792
Max Act: 2.8624. Min Act: -0.0001
Data Index: 754280 (C4 (Web Text))
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2792. Min Range: -3.2792
Max Act: 2.6687. Min Act: -0.0001
Data Index: 588613 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2792. Min Range: -3.2792
Max Act: 2.9243. Min Act: -0.0001
Data Index: 1345114 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2792. Min Range: -3.2792
Max Act: 2.2272. Min Act: -0.0001
Data Index: 1119825 (C4 (Web Text))
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2792. Min Range: -3.2792
Max Act: 2.3166. Min Act: -0.0001
Data Index: 233651 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2792. Min Range: -3.2792
Max Act: 2.6410. Min Act: -0.0001
Data Index: 599463 (C4 (Web Text))
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2792. Min Range: -3.2792
Max Act: 2.4162. Min Act: -0.0001
Data Index: 1133874 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2792. Min Range: -3.2792
Max Act: 1.7991. Min Act: -0.0000
Data Index: 1277531 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2792. Min Range: -3.2792
Max Act: 2.1006. Min Act: -0.0001
Data Index: 180220 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2792. Min Range: -3.2792
Max Act: 2.1798. Min Act: -0.0001
Data Index: 719878 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2792. Min Range: -3.2792
Max Act: 2.2692. Min Act: -0.0001
Data Index: 307405 (C4 (Web Text))
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2792. Min Range: -3.2792
Max Act: 2.0271. Min Act: -0.0001
Data Index: 329262 (C4 (Web Text))
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2792. Min Range: -3.2792
Max Act: 2.0318. Min Act: -0.0001
Data Index: 54986 (C4 (Web Text))
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2792. Min Range: -3.2792
Max Act: 1.9216. Min Act: -0.0001
Data Index: 864408 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2792. Min Range: -3.2792
Max Act: 2.0313. Min Act: -0.0001
Data Index: 1158661 (C4 (Web Text))
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2792. Min Range: -3.2792
Max Act: 2.0117. Min Act: -0.0001
Data Index: 267822 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2792. Min Range: -3.2792
Max Act: 2.2357. Min Act: -0.0001
Data Index: 509357 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19