Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3928 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.4249. Min Range: -1.4249
Max Act: 1.4249. Min Act: -0.0001
Data Index: 239700 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4249. Min Range: -1.4249
Max Act: 1.4172. Min Act: -0.0001
Data Index: 732689 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4249. Min Range: -1.4249
Max Act: 1.3331. Min Act: -0.0001
Data Index: 208693 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4249. Min Range: -1.4249
Max Act: 1.3186. Min Act: -0.0001
Data Index: 579785 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4249. Min Range: -1.4249
Max Act: 1.3543. Min Act: -0.0001
Data Index: 31603 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4249. Min Range: -1.4249
Max Act: 1.2629. Min Act: -0.0001
Data Index: 337994 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4249. Min Range: -1.4249
Max Act: 1.0780. Min Act: -0.0001
Data Index: 775890 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4249. Min Range: -1.4249
Max Act: 1.2602. Min Act: -0.0001
Data Index: 491978 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4249. Min Range: -1.4249
Max Act: 1.2212. Min Act: -0.0001
Data Index: 1212828 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4249. Min Range: -1.4249
Max Act: 1.2944. Min Act: -0.0001
Data Index: 1346468 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4249. Min Range: -1.4249
Max Act: 1.3386. Min Act: -0.0001
Data Index: 454203 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4249. Min Range: -1.4249
Max Act: 1.2485. Min Act: -0.0001
Data Index: 489270 (C4 (Web Text))
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4249. Min Range: -1.4249
Max Act: 1.2310. Min Act: -0.0001
Data Index: 814471 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4249. Min Range: -1.4249
Max Act: 1.2231. Min Act: -0.0001
Data Index: 787353 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4249. Min Range: -1.4249
Max Act: 1.2627. Min Act: -0.0001
Data Index: 738480 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4249. Min Range: -1.4249
Max Act: 1.2246. Min Act: -0.0001
Data Index: 739279 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4249. Min Range: -1.4249
Max Act: 1.2242. Min Act: -0.0001
Data Index: 1146241 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4249. Min Range: -1.4249
Max Act: 1.1828. Min Act: -0.0001
Data Index: 227300 (C4 (Web Text))
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4249. Min Range: -1.4249
Max Act: 1.2202. Min Act: -0.0001
Data Index: 721557 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4249. Min Range: -1.4249
Max Act: 1.2158. Min Act: -0.0001
Data Index: 182095 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19