Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4526 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.4717. Min Range: -1.4717
Max Act: 1.4717. Min Act: -0.0001
Data Index: 546283 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4717. Min Range: -1.4717
Max Act: 1.3305. Min Act: -0.0001
Data Index: 638064 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4717. Min Range: -1.4717
Max Act: 1.3487. Min Act: -0.0001
Data Index: 1163933 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4717. Min Range: -1.4717
Max Act: 1.0936. Min Act: -0.0001
Data Index: 153400 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4717. Min Range: -1.4717
Max Act: 1.1544. Min Act: -0.0001
Data Index: 787763 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4717. Min Range: -1.4717
Max Act: 1.1294. Min Act: -0.0001
Data Index: 1057005 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4717. Min Range: -1.4717
Max Act: 1.0945. Min Act: -0.0001
Data Index: 80665 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4717. Min Range: -1.4717
Max Act: 1.0286. Min Act: -0.0001
Data Index: 655330 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4717. Min Range: -1.4717
Max Act: 1.0994. Min Act: -0.0001
Data Index: 1053133 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4717. Min Range: -1.4717
Max Act: 1.0175. Min Act: -0.0001
Data Index: 511983 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4717. Min Range: -1.4717
Max Act: 1.0540. Min Act: -0.0001
Data Index: 1076348 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4717. Min Range: -1.4717
Max Act: 0.9693. Min Act: -0.0001
Data Index: 710961 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4717. Min Range: -1.4717
Max Act: 0.9574. Min Act: -0.0001
Data Index: 977982 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4717. Min Range: -1.4717
Max Act: 1.0272. Min Act: -0.0001
Data Index: 325980 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4717. Min Range: -1.4717
Max Act: 0.9770. Min Act: -0.0001
Data Index: 312105 (C4 (Web Text))
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4717. Min Range: -1.4717
Max Act: 1.0061. Min Act: -0.0001
Data Index: 321244 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4717. Min Range: -1.4717
Max Act: 0.9870. Min Act: -0.0001
Data Index: 1252784 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4717. Min Range: -1.4717
Max Act: 0.9716. Min Act: -0.0001
Data Index: 551232 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4717. Min Range: -1.4717
Max Act: 0.9383. Min Act: -0.0001
Data Index: 304813 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4717. Min Range: -1.4717
Max Act: 0.9123. Min Act: -0.0001
Data Index: 1289505 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19