Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4492 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 3.1498. Min Range: -3.1498
Max Act: 3.1498. Min Act: -0.0001
Data Index: 238743 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1498. Min Range: -3.1498
Max Act: 2.9894. Min Act: -0.0001
Data Index: 1056596 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1498. Min Range: -3.1498
Max Act: 2.9914. Min Act: -0.0001
Data Index: 348829 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1498. Min Range: -3.1498
Max Act: 3.0902. Min Act: -0.0001
Data Index: 12407 (C4 (Web Text))
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1498. Min Range: -3.1498
Max Act: 2.9634. Min Act: -0.0001
Data Index: 686472 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1498. Min Range: -3.1498
Max Act: 2.5737. Min Act: -0.0001
Data Index: 461426 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1498. Min Range: -3.1498
Max Act: 2.4438. Min Act: -0.0001
Data Index: 177302 (C4 (Web Text))
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1498. Min Range: -3.1498
Max Act: 2.5536. Min Act: -0.0001
Data Index: 1171362 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1498. Min Range: -3.1498
Max Act: 2.4927. Min Act: -0.0001
Data Index: 329221 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1498. Min Range: -3.1498
Max Act: 2.9368. Min Act: -0.0001
Data Index: 1262310 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1498. Min Range: -3.1498
Max Act: 2.5041. Min Act: -0.0001
Data Index: 1166689 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1498. Min Range: -3.1498
Max Act: 1.9121. Min Act: -0.0001
Data Index: 572446 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1498. Min Range: -3.1498
Max Act: 2.1128. Min Act: -0.0001
Data Index: 1101495 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1498. Min Range: -3.1498
Max Act: 2.2092. Min Act: -0.0001
Data Index: 1337140 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1498. Min Range: -3.1498
Max Act: 2.4115. Min Act: -0.0001
Data Index: 384086 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1498. Min Range: -3.1498
Max Act: 2.2966. Min Act: -0.0001
Data Index: 326933 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1498. Min Range: -3.1498
Max Act: 2.2924. Min Act: -0.0001
Data Index: 1278685 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1498. Min Range: -3.1498
Max Act: 2.2644. Min Act: -0.0001
Data Index: 1271690 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1498. Min Range: -3.1498
Max Act: 2.2883. Min Act: -0.0001
Data Index: 1061937 (C4 (Web Text))
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1498. Min Range: -3.1498
Max Act: 2.0400. Min Act: -0.0001
Data Index: 1194050 (C4 (Web Text))
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19