Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3696 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.1543. Min Range: -1.1543
Max Act: 1.1525. Min Act: -0.0002
Data Index: 890149 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1543. Min Range: -1.1543
Max Act: 1.1543. Min Act: -0.0001
Data Index: 879225 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1543. Min Range: -1.1543
Max Act: 1.0424. Min Act: -0.0001
Data Index: 232898 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1543. Min Range: -1.1543
Max Act: 1.0692. Min Act: -0.0001
Data Index: 195547 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1543. Min Range: -1.1543
Max Act: 0.9023. Min Act: -0.0001
Data Index: 255112 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1543. Min Range: -1.1543
Max Act: 1.0908. Min Act: -0.0001
Data Index: 330670 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1543. Min Range: -1.1543
Max Act: 0.9596. Min Act: -0.0001
Data Index: 1272124 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1543. Min Range: -1.1543
Max Act: 0.9653. Min Act: -0.0001
Data Index: 78515 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1543. Min Range: -1.1543
Max Act: 0.9382. Min Act: -0.0001
Data Index: 1138161 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1543. Min Range: -1.1543
Max Act: 0.9760. Min Act: -0.0001
Data Index: 1082538 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1543. Min Range: -1.1543
Max Act: 0.9732. Min Act: -0.0001
Data Index: 417610 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1543. Min Range: -1.1543
Max Act: 0.9459. Min Act: -0.0001
Data Index: 677307 (C4 (Web Text))
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1543. Min Range: -1.1543
Max Act: 0.9593. Min Act: -0.0001
Data Index: 3266 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1543. Min Range: -1.1543
Max Act: 0.9653. Min Act: -0.0001
Data Index: 732429 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1543. Min Range: -1.1543
Max Act: 0.8406. Min Act: -0.0001
Data Index: 235819 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1543. Min Range: -1.1543
Max Act: 0.8154. Min Act: -0.0001
Data Index: 149244 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1543. Min Range: -1.1543
Max Act: 0.8698. Min Act: -0.0001
Data Index: 1138636 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1543. Min Range: -1.1543
Max Act: 0.8229. Min Act: -0.0001
Data Index: 198998 (C4 (Web Text))
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1543. Min Range: -1.1543
Max Act: 0.8513. Min Act: -0.0001
Data Index: 145141 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1543. Min Range: -1.1543
Max Act: 0.8954. Min Act: -0.0001
Data Index: 676477 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19