Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5754 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.4525. Min Range: -3.4525
Max Act: 3.3364. Min Act: -0.0001
Data Index: 497067 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4525. Min Range: -3.4525
Max Act: 3.4525. Min Act: -0.0001
Data Index: 620499 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4525. Min Range: -3.4525
Max Act: 3.1590. Min Act: -0.0001
Data Index: 19556 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4525. Min Range: -3.4525
Max Act: 3.2029. Min Act: -0.0001
Data Index: 300431 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4525. Min Range: -3.4525
Max Act: 2.9981. Min Act: -0.0001
Data Index: 875628 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4525. Min Range: -3.4525
Max Act: 3.0574. Min Act: -0.0001
Data Index: 218495 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4525. Min Range: -3.4525
Max Act: 2.8844. Min Act: -0.0001
Data Index: 410339 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4525. Min Range: -3.4525
Max Act: 2.7133. Min Act: -0.0001
Data Index: 1290779 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4525. Min Range: -3.4525
Max Act: 2.3755. Min Act: -0.0001
Data Index: 553883 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4525. Min Range: -3.4525
Max Act: 2.6162. Min Act: -0.0001
Data Index: 886676 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4525. Min Range: -3.4525
Max Act: 2.6049. Min Act: -0.0001
Data Index: 1309541 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4525. Min Range: -3.4525
Max Act: 2.5707. Min Act: -0.0001
Data Index: 1557682 (Python Code)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4525. Min Range: -3.4525
Max Act: 2.6543. Min Act: -0.0001
Data Index: 1379140 (Python Code)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4525. Min Range: -3.4525
Max Act: 2.6516. Min Act: -0.0001
Data Index: 484021 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4525. Min Range: -3.4525
Max Act: 2.8706. Min Act: -0.0001
Data Index: 785063 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4525. Min Range: -3.4525
Max Act: 2.8481. Min Act: -0.0001
Data Index: 43482 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4525. Min Range: -3.4525
Max Act: 2.4512. Min Act: -0.0001
Data Index: 619260 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4525. Min Range: -3.4525
Max Act: 2.4575. Min Act: -0.0001
Data Index: 115210 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4525. Min Range: -3.4525
Max Act: 2.3438. Min Act: -0.0001
Data Index: 283732 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4525. Min Range: -3.4525
Max Act: 2.4556. Min Act: -0.0001
Data Index: 744499 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19