Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3020 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.5923. Min Range: -0.5923
Max Act: 0.5923. Min Act: -0.0001
Data Index: 764072 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5923. Min Range: -0.5923
Max Act: 0.4838. Min Act: -0.0001
Data Index: 333301 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5923. Min Range: -0.5923
Max Act: 0.4794. Min Act: -0.0001
Data Index: 1226285 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5923. Min Range: -0.5923
Max Act: 0.4620. Min Act: -0.0001
Data Index: 172493 (C4 (Web Text))
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5923. Min Range: -0.5923
Max Act: 0.4848. Min Act: -0.0001
Data Index: 1244850 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5923. Min Range: -0.5923
Max Act: 0.4664. Min Act: -0.0001
Data Index: 199495 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5923. Min Range: -0.5923
Max Act: 0.4381. Min Act: -0.0001
Data Index: 515353 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5923. Min Range: -0.5923
Max Act: 0.4569. Min Act: -0.0001
Data Index: 232096 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5923. Min Range: -0.5923
Max Act: 0.4529. Min Act: -0.0001
Data Index: 911471 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5923. Min Range: -0.5923
Max Act: 0.4508. Min Act: -0.0001
Data Index: 978446 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5923. Min Range: -0.5923
Max Act: 0.4129. Min Act: -0.0001
Data Index: 86337 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5923. Min Range: -0.5923
Max Act: 0.4250. Min Act: -0.0001
Data Index: 1106805 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5923. Min Range: -0.5923
Max Act: 0.4097. Min Act: -0.0001
Data Index: 890067 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5923. Min Range: -0.5923
Max Act: 0.4384. Min Act: -0.0001
Data Index: 1215832 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5923. Min Range: -0.5923
Max Act: 0.4027. Min Act: -0.0001
Data Index: 612881 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5923. Min Range: -0.5923
Max Act: 0.4007. Min Act: -0.0001
Data Index: 382324 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5923. Min Range: -0.5923
Max Act: 0.3747. Min Act: -0.0001
Data Index: 1261709 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5923. Min Range: -0.5923
Max Act: 0.4121. Min Act: -0.0001
Data Index: 1314800 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5923. Min Range: -0.5923
Max Act: 0.4101. Min Act: -0.0001
Data Index: 582457 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5923. Min Range: -0.5923
Max Act: 0.4241. Min Act: -0.0001
Data Index: 327400 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19