Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1787 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.8132. Min Range: -2.8132
Max Act: 2.8132. Min Act: -0.0001
Data Index: 529220 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8132. Min Range: -2.8132
Max Act: 2.3217. Min Act: -0.0001
Data Index: 14023 (C4 (Web Text))
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8132. Min Range: -2.8132
Max Act: 2.1321. Min Act: -0.0001
Data Index: 429282 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8132. Min Range: -2.8132
Max Act: 1.9172. Min Act: -0.0001
Data Index: 594785 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8132. Min Range: -2.8132
Max Act: 2.0450. Min Act: -0.0001
Data Index: 1072152 (C4 (Web Text))
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8132. Min Range: -2.8132
Max Act: 1.8933. Min Act: -0.0001
Data Index: 881221 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8132. Min Range: -2.8132
Max Act: 1.7230. Min Act: -0.0001
Data Index: 159030 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8132. Min Range: -2.8132
Max Act: 1.8119. Min Act: -0.0001
Data Index: 1310398 (C4 (Web Text))
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8132. Min Range: -2.8132
Max Act: 1.7703. Min Act: -0.0001
Data Index: 110435 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8132. Min Range: -2.8132
Max Act: 1.9467. Min Act: -0.0001
Data Index: 913894 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8132. Min Range: -2.8132
Max Act: 1.7251. Min Act: -0.0001
Data Index: 1146049 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8132. Min Range: -2.8132
Max Act: 1.6828. Min Act: -0.0001
Data Index: 912439 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8132. Min Range: -2.8132
Max Act: 1.5714. Min Act: -0.0001
Data Index: 633393 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8132. Min Range: -2.8132
Max Act: 1.6411. Min Act: -0.0001
Data Index: 656911 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8132. Min Range: -2.8132
Max Act: 1.7415. Min Act: -0.0001
Data Index: 73694 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8132. Min Range: -2.8132
Max Act: 1.7020. Min Act: -0.0001
Data Index: 69029 (C4 (Web Text))
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8132. Min Range: -2.8132
Max Act: 1.4916. Min Act: -0.0001
Data Index: 700607 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8132. Min Range: -2.8132
Max Act: 1.4809. Min Act: -0.0001
Data Index: 623320 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8132. Min Range: -2.8132
Max Act: 1.4859. Min Act: -0.0001
Data Index: 167265 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8132. Min Range: -2.8132
Max Act: 1.7490. Min Act: -0.0001
Data Index: 1110338 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19