Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2236 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.4945. Min Range: -0.4945
Max Act: 0.4945. Min Act: -0.0001
Data Index: 751364 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4945. Min Range: -0.4945
Max Act: 0.4705. Min Act: -0.0001
Data Index: 187039 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4945. Min Range: -0.4945
Max Act: 0.4646. Min Act: -0.0001
Data Index: 39474 (C4 (Web Text))
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4945. Min Range: -0.4945
Max Act: 0.4317. Min Act: -0.0001
Data Index: 853764 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4945. Min Range: -0.4945
Max Act: 0.4401. Min Act: -0.0001
Data Index: 346063 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4945. Min Range: -0.4945
Max Act: 0.4527. Min Act: -0.0001
Data Index: 744706 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4945. Min Range: -0.4945
Max Act: 0.4163. Min Act: -0.0001
Data Index: 682564 (C4 (Web Text))
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4945. Min Range: -0.4945
Max Act: 0.4418. Min Act: -0.0001
Data Index: 565085 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4945. Min Range: -0.4945
Max Act: 0.3863. Min Act: -0.0001
Data Index: 646231 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4945. Min Range: -0.4945
Max Act: 0.3979. Min Act: -0.0001
Data Index: 889466 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4945. Min Range: -0.4945
Max Act: 0.3964. Min Act: -0.0001
Data Index: 929872 (C4 (Web Text))
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4945. Min Range: -0.4945
Max Act: 0.4044. Min Act: -0.0001
Data Index: 964144 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4945. Min Range: -0.4945
Max Act: 0.4055. Min Act: -0.0001
Data Index: 254628 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4945. Min Range: -0.4945
Max Act: 0.3871. Min Act: -0.0001
Data Index: 1172522 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4945. Min Range: -0.4945
Max Act: 0.3851. Min Act: -0.0001
Data Index: 616306 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4945. Min Range: -0.4945
Max Act: 0.3681. Min Act: -0.0001
Data Index: 1263423 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4945. Min Range: -0.4945
Max Act: 0.3669. Min Act: -0.0001
Data Index: 992737 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4945. Min Range: -0.4945
Max Act: 0.3623. Min Act: -0.0001
Data Index: 476599 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4945. Min Range: -0.4945
Max Act: 0.3789. Min Act: -0.0001
Data Index: 933708 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4945. Min Range: -0.4945
Max Act: 0.3865. Min Act: -0.0001
Data Index: 847214 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19