Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3223 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.8385. Min Range: -2.8385
Max Act: 2.6307. Min Act: -0.0001
Data Index: 336637 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8385. Min Range: -2.8385
Max Act: 2.8385. Min Act: -0.0001
Data Index: 1180 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8385. Min Range: -2.8385
Max Act: 2.4569. Min Act: -0.0000
Data Index: 876366 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8385. Min Range: -2.8385
Max Act: 2.4358. Min Act: -0.0001
Data Index: 926548 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8385. Min Range: -2.8385
Max Act: 2.1524. Min Act: -0.0000
Data Index: 1051431 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8385. Min Range: -2.8385
Max Act: 2.2656. Min Act: -0.0001
Data Index: 1284240 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8385. Min Range: -2.8385
Max Act: 1.8594. Min Act: -0.0001
Data Index: 236778 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8385. Min Range: -2.8385
Max Act: 2.3806. Min Act: -0.0000
Data Index: 965755 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8385. Min Range: -2.8385
Max Act: 2.0074. Min Act: -0.0001
Data Index: 541736 (C4 (Web Text))
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8385. Min Range: -2.8385
Max Act: 1.9951. Min Act: -0.0001
Data Index: 507964 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8385. Min Range: -2.8385
Max Act: 2.0761. Min Act: -0.0001
Data Index: 836525 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8385. Min Range: -2.8385
Max Act: 2.0377. Min Act: -0.0001
Data Index: 313776 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8385. Min Range: -2.8385
Max Act: 1.9179. Min Act: -0.0001
Data Index: 785914 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8385. Min Range: -2.8385
Max Act: 1.8867. Min Act: -0.0000
Data Index: 332003 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8385. Min Range: -2.8385
Max Act: 1.9641. Min Act: -0.0000
Data Index: 1467696 (Python Code)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8385. Min Range: -2.8385
Max Act: 2.1254. Min Act: -0.0001
Data Index: 1284294 (C4 (Web Text))
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8385. Min Range: -2.8385
Max Act: 1.7407. Min Act: -0.0001
Data Index: 827529 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8385. Min Range: -2.8385
Max Act: 1.8277. Min Act: -0.0001
Data Index: 940954 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8385. Min Range: -2.8385
Max Act: 1.6689. Min Act: -0.0000
Data Index: 1109118 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8385. Min Range: -2.8385
Max Act: 1.8370. Min Act: -0.0001
Data Index: 1432596 (Python Code)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19