Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 741 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.8273. Min Range: -1.8273
Max Act: 1.6948. Min Act: -0.0001
Data Index: 1212280 (C4 (Web Text))
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8273. Min Range: -1.8273
Max Act: 1.8273. Min Act: -0.0001
Data Index: 473282 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8273. Min Range: -1.8273
Max Act: 1.6629. Min Act: -0.0001
Data Index: 815784 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8273. Min Range: -1.8273
Max Act: 1.6929. Min Act: -0.0001
Data Index: 1322320 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8273. Min Range: -1.8273
Max Act: 1.6002. Min Act: -0.0001
Data Index: 718083 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8273. Min Range: -1.8273
Max Act: 1.6183. Min Act: -0.0001
Data Index: 469774 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8273. Min Range: -1.8273
Max Act: 1.7127. Min Act: -0.0001
Data Index: 935543 (C4 (Web Text))
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8273. Min Range: -1.8273
Max Act: 1.5973. Min Act: -0.0001
Data Index: 1216182 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8273. Min Range: -1.8273
Max Act: 1.6615. Min Act: -0.0001
Data Index: 1297093 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8273. Min Range: -1.8273
Max Act: 1.5096. Min Act: -0.0001
Data Index: 1063871 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8273. Min Range: -1.8273
Max Act: 1.4573. Min Act: -0.0001
Data Index: 407019 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8273. Min Range: -1.8273
Max Act: 1.7934. Min Act: -0.0001
Data Index: 1096437 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8273. Min Range: -1.8273
Max Act: 1.5543. Min Act: -0.0001
Data Index: 223703 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8273. Min Range: -1.8273
Max Act: 1.4885. Min Act: -0.0001
Data Index: 893439 (C4 (Web Text))
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8273. Min Range: -1.8273
Max Act: 1.4066. Min Act: -0.0001
Data Index: 726001 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8273. Min Range: -1.8273
Max Act: 1.4764. Min Act: -0.0001
Data Index: 1264701 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8273. Min Range: -1.8273
Max Act: 1.3309. Min Act: -0.0001
Data Index: 1050769 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8273. Min Range: -1.8273
Max Act: 1.4010. Min Act: -0.0001
Data Index: 891558 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8273. Min Range: -1.8273
Max Act: 1.4394. Min Act: -0.0001
Data Index: 1061066 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8273. Min Range: -1.8273
Max Act: 1.4308. Min Act: -0.0001
Data Index: 1269306 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19