Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3306 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.9273. Min Range: -2.9273
Max Act: 2.9273. Min Act: -0.0001
Data Index: 167648 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9273. Min Range: -2.9273
Max Act: 2.7229. Min Act: -0.0001
Data Index: 1314817 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9273. Min Range: -2.9273
Max Act: 2.5543. Min Act: -0.0001
Data Index: 925611 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9273. Min Range: -2.9273
Max Act: 2.1912. Min Act: -0.0001
Data Index: 353867 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9273. Min Range: -2.9273
Max Act: 2.1623. Min Act: -0.0001
Data Index: 1183460 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9273. Min Range: -2.9273
Max Act: 2.3560. Min Act: -0.0000
Data Index: 1133893 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9273. Min Range: -2.9273
Max Act: 2.2305. Min Act: -0.0001
Data Index: 1277242 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9273. Min Range: -2.9273
Max Act: 2.3729. Min Act: -0.0001
Data Index: 1020445 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9273. Min Range: -2.9273
Max Act: 2.2199. Min Act: -0.0001
Data Index: 69469 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9273. Min Range: -2.9273
Max Act: 2.1013. Min Act: -0.0001
Data Index: 757215 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9273. Min Range: -2.9273
Max Act: 2.1039. Min Act: -0.0000
Data Index: 485915 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9273. Min Range: -2.9273
Max Act: 2.1735. Min Act: -0.0001
Data Index: 756638 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9273. Min Range: -2.9273
Max Act: 2.2496. Min Act: -0.0001
Data Index: 399180 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9273. Min Range: -2.9273
Max Act: 2.1531. Min Act: -0.0001
Data Index: 338410 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9273. Min Range: -2.9273
Max Act: 2.1232. Min Act: -0.0001
Data Index: 199222 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9273. Min Range: -2.9273
Max Act: 2.1234. Min Act: -0.0001
Data Index: 376539 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9273. Min Range: -2.9273
Max Act: 2.0005. Min Act: -0.0001
Data Index: 966398 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9273. Min Range: -2.9273
Max Act: 1.9576. Min Act: -0.0001
Data Index: 927507 (C4 (Web Text))
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9273. Min Range: -2.9273
Max Act: 2.0329. Min Act: -0.0001
Data Index: 1075044 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9273. Min Range: -2.9273
Max Act: 1.9924. Min Act: -0.0001
Data Index: 252254 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #19