Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3605 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.8969. Min Range: -3.8969
Max Act: 3.8969. Min Act: -0.0001
Data Index: 1210999 (C4 (Web Text))
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8969. Min Range: -3.8969
Max Act: 3.6896. Min Act: -0.0001
Data Index: 552735 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8969. Min Range: -3.8969
Max Act: 3.8032. Min Act: -0.0001
Data Index: 40798 (C4 (Web Text))
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8969. Min Range: -3.8969
Max Act: 2.5788. Min Act: -0.0001
Data Index: 624616 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8969. Min Range: -3.8969
Max Act: 2.9520. Min Act: -0.0001
Data Index: 1187378 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8969. Min Range: -3.8969
Max Act: 3.0125. Min Act: -0.0001
Data Index: 647690 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8969. Min Range: -3.8969
Max Act: 2.6609. Min Act: -0.0001
Data Index: 1201239 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8969. Min Range: -3.8969
Max Act: 2.4701. Min Act: -0.0001
Data Index: 864604 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8969. Min Range: -3.8969
Max Act: 1.9867. Min Act: -0.0001
Data Index: 1201047 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8969. Min Range: -3.8969
Max Act: 2.0949. Min Act: -0.0001
Data Index: 1214162 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8969. Min Range: -3.8969
Max Act: 2.2107. Min Act: -0.0001
Data Index: 1307248 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8969. Min Range: -3.8969
Max Act: 2.2872. Min Act: -0.0001
Data Index: 435081 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8969. Min Range: -3.8969
Max Act: 2.2175. Min Act: -0.0001
Data Index: 663755 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8969. Min Range: -3.8969
Max Act: 2.2069. Min Act: -0.0001
Data Index: 498553 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8969. Min Range: -3.8969
Max Act: 2.1989. Min Act: -0.0001
Data Index: 339822 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8969. Min Range: -3.8969
Max Act: 2.0513. Min Act: -0.0001
Data Index: 1340840 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8969. Min Range: -3.8969
Max Act: 2.1562. Min Act: -0.0001
Data Index: 1149817 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8969. Min Range: -3.8969
Max Act: 2.1535. Min Act: -0.0001
Data Index: 555022 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8969. Min Range: -3.8969
Max Act: 2.3091. Min Act: -0.0001
Data Index: 1430058 (Python Code)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8969. Min Range: -3.8969
Max Act: 2.1791. Min Act: -0.0001
Data Index: 103674 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19