Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2009 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.6952. Min Range: -0.6952
Max Act: 0.6952. Min Act: -0.0001
Data Index: 989906 (C4 (Web Text))
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6952. Min Range: -0.6952
Max Act: 0.6673. Min Act: -0.0001
Data Index: 1283852 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6952. Min Range: -0.6952
Max Act: 0.6409. Min Act: -0.0001
Data Index: 734384 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6952. Min Range: -0.6952
Max Act: 0.6500. Min Act: -0.0001
Data Index: 701682 (C4 (Web Text))
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6952. Min Range: -0.6952
Max Act: 0.5981. Min Act: -0.0001
Data Index: 428374 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6952. Min Range: -0.6952
Max Act: 0.5395. Min Act: -0.0001
Data Index: 202769 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6952. Min Range: -0.6952
Max Act: 0.6187. Min Act: -0.0001
Data Index: 742519 (C4 (Web Text))
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6952. Min Range: -0.6952
Max Act: 0.5834. Min Act: -0.0001
Data Index: 564208 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6952. Min Range: -0.6952
Max Act: 0.6208. Min Act: -0.0001
Data Index: 405575 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6952. Min Range: -0.6952
Max Act: 0.5928. Min Act: -0.0001
Data Index: 1305736 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6952. Min Range: -0.6952
Max Act: 0.5847. Min Act: -0.0001
Data Index: 769301 (C4 (Web Text))
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6952. Min Range: -0.6952
Max Act: 0.5897. Min Act: -0.0001
Data Index: 305454 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6952. Min Range: -0.6952
Max Act: 0.5540. Min Act: -0.0001
Data Index: 1236058 (C4 (Web Text))
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6952. Min Range: -0.6952
Max Act: 0.5915. Min Act: -0.0001
Data Index: 516120 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6952. Min Range: -0.6952
Max Act: 0.5498. Min Act: -0.0001
Data Index: 347184 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6952. Min Range: -0.6952
Max Act: 0.5443. Min Act: -0.0001
Data Index: 769495 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6952. Min Range: -0.6952
Max Act: 0.5601. Min Act: -0.0001
Data Index: 652637 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6952. Min Range: -0.6952
Max Act: 0.5404. Min Act: -0.0001
Data Index: 282014 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6952. Min Range: -0.6952
Max Act: 0.5430. Min Act: -0.0001
Data Index: 716974 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6952. Min Range: -0.6952
Max Act: 0.5526. Min Act: -0.0001
Data Index: 437291 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19