Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2701 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.6052. Min Range: -1.6052
Max Act: 1.6052. Min Act: -0.0001
Data Index: 228989 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6052. Min Range: -1.6052
Max Act: 1.2633. Min Act: -0.0001
Data Index: 723044 (C4 (Web Text))
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6052. Min Range: -1.6052
Max Act: 1.2488. Min Act: -0.0001
Data Index: 998721 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6052. Min Range: -1.6052
Max Act: 1.1559. Min Act: -0.0001
Data Index: 877697 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6052. Min Range: -1.6052
Max Act: 1.1123. Min Act: -0.0001
Data Index: 153333 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6052. Min Range: -1.6052
Max Act: 1.0630. Min Act: -0.0001
Data Index: 457368 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6052. Min Range: -1.6052
Max Act: 1.1744. Min Act: -0.0001
Data Index: 735606 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6052. Min Range: -1.6052
Max Act: 1.1367. Min Act: -0.0001
Data Index: 1167301 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6052. Min Range: -1.6052
Max Act: 1.1373. Min Act: -0.0001
Data Index: 916588 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6052. Min Range: -1.6052
Max Act: 1.1998. Min Act: -0.0001
Data Index: 803982 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6052. Min Range: -1.6052
Max Act: 1.0175. Min Act: -0.0001
Data Index: 906551 (C4 (Web Text))
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6052. Min Range: -1.6052
Max Act: 1.0234. Min Act: -0.0001
Data Index: 379594 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6052. Min Range: -1.6052
Max Act: 1.1691. Min Act: -0.0001
Data Index: 545634 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6052. Min Range: -1.6052
Max Act: 1.1943. Min Act: -0.0001
Data Index: 200900 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6052. Min Range: -1.6052
Max Act: 1.1788. Min Act: -0.0001
Data Index: 1086708 (C4 (Web Text))
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6052. Min Range: -1.6052
Max Act: 1.0019. Min Act: -0.0001
Data Index: 1331865 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6052. Min Range: -1.6052
Max Act: 1.0076. Min Act: -0.0001
Data Index: 950709 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6052. Min Range: -1.6052
Max Act: 1.1280. Min Act: -0.0001
Data Index: 1278694 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6052. Min Range: -1.6052
Max Act: 1.0967. Min Act: -0.0001
Data Index: 275657 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6052. Min Range: -1.6052
Max Act: 1.0856. Min Act: -0.0001
Data Index: 659135 (C4 (Web Text))
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19