Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2560 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.0553. Min Range: -0.0553
Max Act: 0.0553. Min Act: -0.0001
Data Index: 1122290 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0553. Min Range: -0.0553
Max Act: 0.0533. Min Act: -0.0001
Data Index: 493411 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0553. Min Range: -0.0553
Max Act: 0.0533. Min Act: -0.0001
Data Index: 893683 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0553. Min Range: -0.0553
Max Act: 0.0540. Min Act: -0.0001
Data Index: 145987 (C4 (Web Text))
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0553. Min Range: -0.0553
Max Act: 0.0498. Min Act: -0.0001
Data Index: 585367 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0553. Min Range: -0.0553
Max Act: 0.0499. Min Act: -0.0001
Data Index: 207984 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0553. Min Range: -0.0553
Max Act: 0.0505. Min Act: -0.0001
Data Index: 52806 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0553. Min Range: -0.0553
Max Act: 0.0507. Min Act: -0.0001
Data Index: 1209459 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0553. Min Range: -0.0553
Max Act: 0.0514. Min Act: -0.0001
Data Index: 311977 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0553. Min Range: -0.0553
Max Act: 0.0466. Min Act: -0.0001
Data Index: 735359 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0553. Min Range: -0.0553
Max Act: 0.0514. Min Act: -0.0001
Data Index: 1411529 (Python Code)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0553. Min Range: -0.0553
Max Act: 0.0474. Min Act: -0.0001
Data Index: 1100107 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0553. Min Range: -0.0553
Max Act: 0.0492. Min Act: -0.0001
Data Index: 818410 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0553. Min Range: -0.0553
Max Act: 0.0480. Min Act: -0.0001
Data Index: 1030215 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0553. Min Range: -0.0553
Max Act: 0.0466. Min Act: -0.0001
Data Index: 1133933 (C4 (Web Text))
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0553. Min Range: -0.0553
Max Act: 0.0480. Min Act: -0.0001
Data Index: 903290 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0553. Min Range: -0.0553
Max Act: 0.0501. Min Act: -0.0001
Data Index: 1315385 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0553. Min Range: -0.0553
Max Act: 0.0471. Min Act: -0.0001
Data Index: 195332 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0553. Min Range: -0.0553
Max Act: 0.0486. Min Act: -0.0001
Data Index: 1146148 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0553. Min Range: -0.0553
Max Act: 0.0503. Min Act: -0.0001
Data Index: 939 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19