Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3489 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.7876. Min Range: -1.7876
Max Act: 1.7876. Min Act: -0.0001
Data Index: 1134214 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7876. Min Range: -1.7876
Max Act: 1.4644. Min Act: -0.0001
Data Index: 41167 (C4 (Web Text))
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7876. Min Range: -1.7876
Max Act: 1.3931. Min Act: -0.0001
Data Index: 237470 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7876. Min Range: -1.7876
Max Act: 1.2749. Min Act: -0.0001
Data Index: 38243 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7876. Min Range: -1.7876
Max Act: 1.2485. Min Act: -0.0001
Data Index: 1119661 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7876. Min Range: -1.7876
Max Act: 1.1511. Min Act: -0.0001
Data Index: 649173 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7876. Min Range: -1.7876
Max Act: 1.0592. Min Act: -0.0001
Data Index: 1341631 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7876. Min Range: -1.7876
Max Act: 0.9615. Min Act: -0.0001
Data Index: 1236246 (C4 (Web Text))
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7876. Min Range: -1.7876
Max Act: 0.9801. Min Act: -0.0001
Data Index: 424946 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7876. Min Range: -1.7876
Max Act: 0.9748. Min Act: -0.0001
Data Index: 1587890 (Python Code)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7876. Min Range: -1.7876
Max Act: 0.8864. Min Act: -0.0001
Data Index: 980040 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7876. Min Range: -1.7876
Max Act: 0.9017. Min Act: -0.0001
Data Index: 873213 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7876. Min Range: -1.7876
Max Act: 0.8100. Min Act: -0.0001
Data Index: 862782 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7876. Min Range: -1.7876
Max Act: 0.8860. Min Act: -0.0001
Data Index: 1342693 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7876. Min Range: -1.7876
Max Act: 0.8678. Min Act: -0.0001
Data Index: 373419 (C4 (Web Text))
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7876. Min Range: -1.7876
Max Act: 0.7951. Min Act: -0.0001
Data Index: 1238353 (C4 (Web Text))
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7876. Min Range: -1.7876
Max Act: 0.7477. Min Act: -0.0001
Data Index: 1605952 (Python Code)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7876. Min Range: -1.7876
Max Act: 0.8118. Min Act: -0.0001
Data Index: 996435 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7876. Min Range: -1.7876
Max Act: 0.7950. Min Act: -0.0001
Data Index: 622118 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7876. Min Range: -1.7876
Max Act: 0.7660. Min Act: -0.0001
Data Index: 1049525 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19