Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3686 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.2145. Min Range: -1.2145
Max Act: 1.2145. Min Act: -0.0001
Data Index: 869361 (C4 (Web Text))
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2145. Min Range: -1.2145
Max Act: 1.1382. Min Act: -0.0001
Data Index: 901625 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2145. Min Range: -1.2145
Max Act: 0.9175. Min Act: -0.0001
Data Index: 1234768 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2145. Min Range: -1.2145
Max Act: 0.7858. Min Act: -0.0001
Data Index: 173550 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2145. Min Range: -1.2145
Max Act: 0.7124. Min Act: -0.0001
Data Index: 28558 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2145. Min Range: -1.2145
Max Act: 0.7551. Min Act: -0.0001
Data Index: 1541077 (Python Code)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2145. Min Range: -1.2145
Max Act: 0.7481. Min Act: -0.0001
Data Index: 1331205 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2145. Min Range: -1.2145
Max Act: 0.7428. Min Act: -0.0001
Data Index: 693371 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2145. Min Range: -1.2145
Max Act: 0.8092. Min Act: -0.0001
Data Index: 118312 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2145. Min Range: -1.2145
Max Act: 0.6155. Min Act: -0.0001
Data Index: 1156446 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2145. Min Range: -1.2145
Max Act: 0.6881. Min Act: -0.0001
Data Index: 24163 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2145. Min Range: -1.2145
Max Act: 0.7086. Min Act: -0.0001
Data Index: 299560 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2145. Min Range: -1.2145
Max Act: 0.7162. Min Act: -0.0001
Data Index: 15276 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2145. Min Range: -1.2145
Max Act: 0.6697. Min Act: -0.0001
Data Index: 1071450 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2145. Min Range: -1.2145
Max Act: 0.7722. Min Act: -0.0001
Data Index: 39975 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2145. Min Range: -1.2145
Max Act: 0.6543. Min Act: -0.0001
Data Index: 783808 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2145. Min Range: -1.2145
Max Act: 0.6702. Min Act: -0.0001
Data Index: 441147 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2145. Min Range: -1.2145
Max Act: 0.6266. Min Act: -0.0001
Data Index: 1469820 (Python Code)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2145. Min Range: -1.2145
Max Act: 0.6248. Min Act: -0.0001
Data Index: 1037766 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2145. Min Range: -1.2145
Max Act: 0.5898. Min Act: -0.0001
Data Index: 922995 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19