Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3055 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.8992. Min Range: -1.8992
Max Act: 1.8992. Min Act: -0.0001
Data Index: 610562 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8992. Min Range: -1.8992
Max Act: 1.7973. Min Act: -0.0001
Data Index: 26739 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8992. Min Range: -1.8992
Max Act: 1.5877. Min Act: -0.0001
Data Index: 929712 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8992. Min Range: -1.8992
Max Act: 1.5388. Min Act: -0.0001
Data Index: 106378 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8992. Min Range: -1.8992
Max Act: 1.6076. Min Act: -0.0001
Data Index: 1558022 (Python Code)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8992. Min Range: -1.8992
Max Act: 1.5477. Min Act: -0.0001
Data Index: 269189 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8992. Min Range: -1.8992
Max Act: 1.5346. Min Act: -0.0001
Data Index: 742341 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8992. Min Range: -1.8992
Max Act: 1.4848. Min Act: -0.0001
Data Index: 469475 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8992. Min Range: -1.8992
Max Act: 1.5713. Min Act: -0.0001
Data Index: 477738 (C4 (Web Text))
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8992. Min Range: -1.8992
Max Act: 1.5133. Min Act: -0.0001
Data Index: 1160808 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8992. Min Range: -1.8992
Max Act: 1.5117. Min Act: -0.0001
Data Index: 558525 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8992. Min Range: -1.8992
Max Act: 1.5079. Min Act: -0.0001
Data Index: 908238 (C4 (Web Text))
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8992. Min Range: -1.8992
Max Act: 1.4596. Min Act: -0.0001
Data Index: 546481 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8992. Min Range: -1.8992
Max Act: 1.5092. Min Act: -0.0001
Data Index: 219371 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8992. Min Range: -1.8992
Max Act: 1.4673. Min Act: -0.0001
Data Index: 1491568 (Python Code)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8992. Min Range: -1.8992
Max Act: 1.4967. Min Act: -0.0001
Data Index: 42157 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8992. Min Range: -1.8992
Max Act: 1.4106. Min Act: -0.0001
Data Index: 688608 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8992. Min Range: -1.8992
Max Act: 1.4095. Min Act: -0.0001
Data Index: 1116454 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8992. Min Range: -1.8992
Max Act: 1.3648. Min Act: -0.0001
Data Index: 372298 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8992. Min Range: -1.8992
Max Act: 1.4294. Min Act: -0.0001
Data Index: 930903 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19