Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1694 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.8173. Min Range: -1.8173
Max Act: 1.8173. Min Act: -0.0001
Data Index: 836566 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8173. Min Range: -1.8173
Max Act: 1.4937. Min Act: -0.0001
Data Index: 262360 (C4 (Web Text))
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8173. Min Range: -1.8173
Max Act: 1.4178. Min Act: -0.0001
Data Index: 968878 (C4 (Web Text))
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8173. Min Range: -1.8173
Max Act: 1.1887. Min Act: -0.0001
Data Index: 323407 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8173. Min Range: -1.8173
Max Act: 1.1970. Min Act: -0.0001
Data Index: 1303838 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8173. Min Range: -1.8173
Max Act: 1.1135. Min Act: -0.0001
Data Index: 298566 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8173. Min Range: -1.8173
Max Act: 1.1333. Min Act: -0.0001
Data Index: 1233631 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8173. Min Range: -1.8173
Max Act: 1.1298. Min Act: -0.0001
Data Index: 1304360 (C4 (Web Text))
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8173. Min Range: -1.8173
Max Act: 1.1689. Min Act: -0.0001
Data Index: 789637 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8173. Min Range: -1.8173
Max Act: 1.0873. Min Act: -0.0001
Data Index: 1339505 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8173. Min Range: -1.8173
Max Act: 1.0083. Min Act: -0.0001
Data Index: 1270863 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8173. Min Range: -1.8173
Max Act: 0.9441. Min Act: -0.0001
Data Index: 377445 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8173. Min Range: -1.8173
Max Act: 0.9943. Min Act: -0.0001
Data Index: 243681 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8173. Min Range: -1.8173
Max Act: 0.9972. Min Act: -0.0001
Data Index: 688397 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8173. Min Range: -1.8173
Max Act: 0.9668. Min Act: -0.0001
Data Index: 1054216 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8173. Min Range: -1.8173
Max Act: 0.9017. Min Act: -0.0001
Data Index: 985404 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8173. Min Range: -1.8173
Max Act: 0.9333. Min Act: -0.0001
Data Index: 329020 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8173. Min Range: -1.8173
Max Act: 0.9607. Min Act: -0.0001
Data Index: 679039 (C4 (Web Text))
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8173. Min Range: -1.8173
Max Act: 0.9005. Min Act: -0.0001
Data Index: 741774 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8173. Min Range: -1.8173
Max Act: 0.9178. Min Act: -0.0001
Data Index: 1127046 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #19