Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 798 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.6417. Min Range: -0.6417
Max Act: 0.6417. Min Act: -0.0001
Data Index: 713748 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6417. Min Range: -0.6417
Max Act: 0.5376. Min Act: -0.0001
Data Index: 239344 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6417. Min Range: -0.6417
Max Act: 0.5406. Min Act: -0.0001
Data Index: 534329 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6417. Min Range: -0.6417
Max Act: 0.5271. Min Act: -0.0001
Data Index: 1348167 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6417. Min Range: -0.6417
Max Act: 0.5211. Min Act: -0.0001
Data Index: 680750 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6417. Min Range: -0.6417
Max Act: 0.5536. Min Act: -0.0001
Data Index: 235294 (C4 (Web Text))
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6417. Min Range: -0.6417
Max Act: 0.5520. Min Act: -0.0001
Data Index: 308803 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6417. Min Range: -0.6417
Max Act: 0.5094. Min Act: -0.0001
Data Index: 209198 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6417. Min Range: -0.6417
Max Act: 0.5100. Min Act: -0.0001
Data Index: 519584 (C4 (Web Text))
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6417. Min Range: -0.6417
Max Act: 0.5053. Min Act: -0.0001
Data Index: 85993 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6417. Min Range: -0.6417
Max Act: 0.5221. Min Act: -0.0001
Data Index: 277325 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6417. Min Range: -0.6417
Max Act: 0.4834. Min Act: -0.0001
Data Index: 1013634 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6417. Min Range: -0.6417
Max Act: 0.4825. Min Act: -0.0001
Data Index: 375937 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6417. Min Range: -0.6417
Max Act: 0.5126. Min Act: -0.0001
Data Index: 1017939 (C4 (Web Text))
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6417. Min Range: -0.6417
Max Act: 0.4978. Min Act: -0.0001
Data Index: 1323784 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6417. Min Range: -0.6417
Max Act: 0.4952. Min Act: -0.0001
Data Index: 581339 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6417. Min Range: -0.6417
Max Act: 0.5009. Min Act: -0.0001
Data Index: 319338 (C4 (Web Text))
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6417. Min Range: -0.6417
Max Act: 0.4870. Min Act: -0.0001
Data Index: 1357085 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6417. Min Range: -0.6417
Max Act: 0.4835. Min Act: -0.0001
Data Index: 359256 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6417. Min Range: -0.6417
Max Act: 0.4828. Min Act: -0.0001
Data Index: 107426 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19