Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2413 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.7782. Min Range: -1.7782
Max Act: 1.7782. Min Act: -0.0001
Data Index: 863705 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7782. Min Range: -1.7782
Max Act: 1.5827. Min Act: -0.0001
Data Index: 36639 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7782. Min Range: -1.7782
Max Act: 1.5983. Min Act: -0.0001
Data Index: 1131933 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7782. Min Range: -1.7782
Max Act: 1.5379. Min Act: -0.0001
Data Index: 179565 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7782. Min Range: -1.7782
Max Act: 1.4735. Min Act: -0.0001
Data Index: 255053 (C4 (Web Text))
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7782. Min Range: -1.7782
Max Act: 1.5156. Min Act: -0.0001
Data Index: 904295 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7782. Min Range: -1.7782
Max Act: 1.4761. Min Act: -0.0001
Data Index: 1143385 (C4 (Web Text))
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7782. Min Range: -1.7782
Max Act: 1.5037. Min Act: -0.0001
Data Index: 843554 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7782. Min Range: -1.7782
Max Act: 1.4881. Min Act: -0.0001
Data Index: 1219437 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7782. Min Range: -1.7782
Max Act: 1.5422. Min Act: -0.0001
Data Index: 586440 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7782. Min Range: -1.7782
Max Act: 1.5263. Min Act: -0.0001
Data Index: 478766 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7782. Min Range: -1.7782
Max Act: 1.4779. Min Act: -0.0001
Data Index: 929095 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7782. Min Range: -1.7782
Max Act: 1.4242. Min Act: -0.0001
Data Index: 682441 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7782. Min Range: -1.7782
Max Act: 1.5088. Min Act: -0.0001
Data Index: 528846 (C4 (Web Text))
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7782. Min Range: -1.7782
Max Act: 1.4515. Min Act: -0.0001
Data Index: 1004607 (C4 (Web Text))
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7782. Min Range: -1.7782
Max Act: 1.4506. Min Act: -0.0001
Data Index: 616793 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7782. Min Range: -1.7782
Max Act: 1.3630. Min Act: -0.0001
Data Index: 60418 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7782. Min Range: -1.7782
Max Act: 1.4834. Min Act: -0.0001
Data Index: 557139 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7782. Min Range: -1.7782
Max Act: 1.4227. Min Act: -0.0001
Data Index: 1109762 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7782. Min Range: -1.7782
Max Act: 1.3956. Min Act: -0.0001
Data Index: 679210 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19