Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5781 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 4.2476. Min Range: -4.2476
Max Act: 4.2476. Min Act: -0.0001
Data Index: 167192 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2476. Min Range: -4.2476
Max Act: 3.0192. Min Act: -0.0000
Data Index: 628599 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2476. Min Range: -4.2476
Max Act: 2.9050. Min Act: -0.0001
Data Index: 1017275 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2476. Min Range: -4.2476
Max Act: 2.7747. Min Act: -0.0001
Data Index: 979777 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2476. Min Range: -4.2476
Max Act: 2.9259. Min Act: -0.0001
Data Index: 352350 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2476. Min Range: -4.2476
Max Act: 2.6360. Min Act: -0.0001
Data Index: 613051 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2476. Min Range: -4.2476
Max Act: 2.4337. Min Act: -0.0001
Data Index: 593400 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2476. Min Range: -4.2476
Max Act: 2.4801. Min Act: -0.0001
Data Index: 221958 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2476. Min Range: -4.2476
Max Act: 2.5065. Min Act: -0.0001
Data Index: 504305 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2476. Min Range: -4.2476
Max Act: 2.4563. Min Act: -0.0000
Data Index: 127528 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2476. Min Range: -4.2476
Max Act: 2.5166. Min Act: -0.0001
Data Index: 752530 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2476. Min Range: -4.2476
Max Act: 2.5059. Min Act: -0.0000
Data Index: 1276091 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2476. Min Range: -4.2476
Max Act: 2.3534. Min Act: -0.0001
Data Index: 794849 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2476. Min Range: -4.2476
Max Act: 2.2321. Min Act: -0.0001
Data Index: 389425 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2476. Min Range: -4.2476
Max Act: 2.3437. Min Act: -0.0000
Data Index: 1006152 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2476. Min Range: -4.2476
Max Act: 2.2187. Min Act: -0.0001
Data Index: 247250 (C4 (Web Text))
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2476. Min Range: -4.2476
Max Act: 2.1841. Min Act: -0.0001
Data Index: 339280 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2476. Min Range: -4.2476
Max Act: 2.2102. Min Act: -0.0001
Data Index: 645357 (C4 (Web Text))
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2476. Min Range: -4.2476
Max Act: 2.2982. Min Act: -0.0000
Data Index: 749673 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2476. Min Range: -4.2476
Max Act: 2.0663. Min Act: -0.0001
Data Index: 595806 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19