Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3262 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.0572. Min Range: -0.0572
Max Act: 0.0566. Min Act: -0.0002
Data Index: 51196 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0572. Min Range: -0.0572
Max Act: 0.0572. Min Act: -0.0001
Data Index: 97594 (C4 (Web Text))
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0572. Min Range: -0.0572
Max Act: 0.0489. Min Act: -0.0001
Data Index: 215503 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0572. Min Range: -0.0572
Max Act: 0.0500. Min Act: -0.0001
Data Index: 879801 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0572. Min Range: -0.0572
Max Act: 0.0498. Min Act: -0.0001
Data Index: 1469817 (Python Code)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0572. Min Range: -0.0572
Max Act: 0.0493. Min Act: -0.0001
Data Index: 818328 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0572. Min Range: -0.0572
Max Act: 0.0487. Min Act: -0.0001
Data Index: 1530582 (Python Code)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0572. Min Range: -0.0572
Max Act: 0.0498. Min Act: -0.0001
Data Index: 1623184 (Python Code)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0572. Min Range: -0.0572
Max Act: 0.0483. Min Act: -0.0001
Data Index: 1231468 (C4 (Web Text))
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0572. Min Range: -0.0572
Max Act: 0.0490. Min Act: -0.0001
Data Index: 264058 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0572. Min Range: -0.0572
Max Act: 0.0467. Min Act: -0.0001
Data Index: 38552 (C4 (Web Text))
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0572. Min Range: -0.0572
Max Act: 0.0473. Min Act: -0.0001
Data Index: 1586267 (Python Code)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0572. Min Range: -0.0572
Max Act: 0.0453. Min Act: -0.0001
Data Index: 1493372 (Python Code)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0572. Min Range: -0.0572
Max Act: 0.0438. Min Act: -0.0001
Data Index: 1324862 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0572. Min Range: -0.0572
Max Act: 0.0469. Min Act: -0.0001
Data Index: 298502 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0572. Min Range: -0.0572
Max Act: 0.0438. Min Act: -0.0001
Data Index: 409460 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0572. Min Range: -0.0572
Max Act: 0.0442. Min Act: -0.0001
Data Index: 1565417 (Python Code)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0572. Min Range: -0.0572
Max Act: 0.0422. Min Act: -0.0001
Data Index: 189500 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0572. Min Range: -0.0572
Max Act: 0.0419. Min Act: -0.0001
Data Index: 880518 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0572. Min Range: -0.0572
Max Act: 0.0448. Min Act: -0.0001
Data Index: 1519564 (Python Code)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19