Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 14 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 1.3366. Min Range: -1.3366
Max Act: 1.3366. Min Act: -0.0001
Data Index: 1258431 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3366. Min Range: -1.3366
Max Act: 1.2481. Min Act: -0.0001
Data Index: 492430 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3366. Min Range: -1.3366
Max Act: 1.0772. Min Act: -0.0001
Data Index: 978236 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3366. Min Range: -1.3366
Max Act: 1.0161. Min Act: -0.0001
Data Index: 307754 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3366. Min Range: -1.3366
Max Act: 1.0418. Min Act: -0.0001
Data Index: 860158 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3366. Min Range: -1.3366
Max Act: 0.9690. Min Act: -0.0001
Data Index: 220646 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3366. Min Range: -1.3366
Max Act: 0.9290. Min Act: -0.0001
Data Index: 1305146 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3366. Min Range: -1.3366
Max Act: 0.8323. Min Act: -0.0001
Data Index: 1119763 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3366. Min Range: -1.3366
Max Act: 0.8495. Min Act: -0.0001
Data Index: 346031 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3366. Min Range: -1.3366
Max Act: 0.6381. Min Act: -0.0001
Data Index: 1202608 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3366. Min Range: -1.3366
Max Act: 0.8037. Min Act: -0.0000
Data Index: 476342 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3366. Min Range: -1.3366
Max Act: 0.9110. Min Act: -0.0001
Data Index: 198034 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3366. Min Range: -1.3366
Max Act: 0.7735. Min Act: -0.0001
Data Index: 1257723 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3366. Min Range: -1.3366
Max Act: 0.8059. Min Act: -0.0001
Data Index: 920534 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3366. Min Range: -1.3366
Max Act: 0.7844. Min Act: -0.0001
Data Index: 1303701 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3366. Min Range: -1.3366
Max Act: 0.7622. Min Act: -0.0001
Data Index: 1332604 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3366. Min Range: -1.3366
Max Act: 0.7142. Min Act: -0.0001
Data Index: 374293 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3366. Min Range: -1.3366
Max Act: 0.7774. Min Act: -0.0001
Data Index: 1162768 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3366. Min Range: -1.3366
Max Act: 0.7301. Min Act: -0.0001
Data Index: 467004 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3366. Min Range: -1.3366
Max Act: 0.7478. Min Act: -0.0001
Data Index: 968731 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19