Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2800 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.0539. Min Range: -0.0539
Max Act: 0.0539. Min Act: -0.0001
Data Index: 1493109 (Python Code)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0539. Min Range: -0.0539
Max Act: 0.0496. Min Act: -0.0001
Data Index: 365612 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0539. Min Range: -0.0539
Max Act: 0.0511. Min Act: -0.0001
Data Index: 1494916 (Python Code)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0539. Min Range: -0.0539
Max Act: 0.0478. Min Act: -0.0001
Data Index: 1511939 (Python Code)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0539. Min Range: -0.0539
Max Act: 0.0450. Min Act: -0.0001
Data Index: 1275637 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0539. Min Range: -0.0539
Max Act: 0.0495. Min Act: -0.0001
Data Index: 1277051 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0539. Min Range: -0.0539
Max Act: 0.0445. Min Act: -0.0001
Data Index: 1140260 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0539. Min Range: -0.0539
Max Act: 0.0431. Min Act: -0.0001
Data Index: 1089416 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0539. Min Range: -0.0539
Max Act: 0.0432. Min Act: -0.0001
Data Index: 123753 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0539. Min Range: -0.0539
Max Act: 0.0441. Min Act: -0.0001
Data Index: 967006 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0539. Min Range: -0.0539
Max Act: 0.0417. Min Act: -0.0001
Data Index: 1409159 (Python Code)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0539. Min Range: -0.0539
Max Act: 0.0472. Min Act: -0.0001
Data Index: 1562520 (Python Code)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0539. Min Range: -0.0539
Max Act: 0.0446. Min Act: -0.0001
Data Index: 1550020 (Python Code)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0539. Min Range: -0.0539
Max Act: 0.0441. Min Act: -0.0001
Data Index: 896096 (C4 (Web Text))
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0539. Min Range: -0.0539
Max Act: 0.0401. Min Act: -0.0001
Data Index: 883816 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0539. Min Range: -0.0539
Max Act: 0.0369. Min Act: -0.0001
Data Index: 751392 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0539. Min Range: -0.0539
Max Act: 0.0414. Min Act: -0.0001
Data Index: 772457 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0539. Min Range: -0.0539
Max Act: 0.0431. Min Act: -0.0001
Data Index: 551896 (C4 (Web Text))
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0539. Min Range: -0.0539
Max Act: 0.0433. Min Act: -0.0001
Data Index: 1472141 (Python Code)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0539. Min Range: -0.0539
Max Act: 0.0386. Min Act: -0.0001
Data Index: 431724 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19