Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2006 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.3178. Min Range: -2.3178
Max Act: 2.3178. Min Act: -0.0001
Data Index: 1074096 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3178. Min Range: -2.3178
Max Act: 2.2663. Min Act: -0.0001
Data Index: 214996 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3178. Min Range: -2.3178
Max Act: 2.2519. Min Act: -0.0001
Data Index: 126288 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3178. Min Range: -2.3178
Max Act: 2.2018. Min Act: -0.0001
Data Index: 694127 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3178. Min Range: -2.3178
Max Act: 2.2133. Min Act: -0.0001
Data Index: 1347498 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3178. Min Range: -2.3178
Max Act: 1.9230. Min Act: -0.0001
Data Index: 202679 (C4 (Web Text))
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3178. Min Range: -2.3178
Max Act: 1.7678. Min Act: -0.0001
Data Index: 614335 (C4 (Web Text))
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3178. Min Range: -2.3178
Max Act: 1.7203. Min Act: -0.0001
Data Index: 377535 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3178. Min Range: -2.3178
Max Act: 1.6711. Min Act: -0.0001
Data Index: 619857 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3178. Min Range: -2.3178
Max Act: 1.6725. Min Act: -0.0001
Data Index: 182626 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3178. Min Range: -2.3178
Max Act: 1.6672. Min Act: -0.0001
Data Index: 111472 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3178. Min Range: -2.3178
Max Act: 1.6077. Min Act: -0.0001
Data Index: 966715 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3178. Min Range: -2.3178
Max Act: 1.6880. Min Act: -0.0001
Data Index: 662264 (C4 (Web Text))
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3178. Min Range: -2.3178
Max Act: 1.5006. Min Act: -0.0001
Data Index: 682592 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3178. Min Range: -2.3178
Max Act: 1.4072. Min Act: -0.0001
Data Index: 384277 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3178. Min Range: -2.3178
Max Act: 1.6403. Min Act: -0.0001
Data Index: 990756 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3178. Min Range: -2.3178
Max Act: 1.6524. Min Act: -0.0001
Data Index: 460550 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3178. Min Range: -2.3178
Max Act: 1.5513. Min Act: -0.0001
Data Index: 949815 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3178. Min Range: -2.3178
Max Act: 1.6348. Min Act: -0.0001
Data Index: 577132 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3178. Min Range: -2.3178
Max Act: 1.4498. Min Act: -0.0001
Data Index: 1328329 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19