Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3433 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.4723. Min Range: -2.4723
Max Act: 2.4723. Min Act: -0.0001
Data Index: 1030650 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4723. Min Range: -2.4723
Max Act: 2.2209. Min Act: -0.0001
Data Index: 1182466 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4723. Min Range: -2.4723
Max Act: 2.2711. Min Act: -0.0001
Data Index: 1294373 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4723. Min Range: -2.4723
Max Act: 2.2363. Min Act: -0.0001
Data Index: 335619 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4723. Min Range: -2.4723
Max Act: 2.1152. Min Act: -0.0001
Data Index: 921235 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4723. Min Range: -2.4723
Max Act: 1.9663. Min Act: -0.0001
Data Index: 620256 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4723. Min Range: -2.4723
Max Act: 1.6396. Min Act: -0.0001
Data Index: 702952 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4723. Min Range: -2.4723
Max Act: 1.7778. Min Act: -0.0001
Data Index: 1198379 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4723. Min Range: -2.4723
Max Act: 1.7908. Min Act: -0.0001
Data Index: 667953 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4723. Min Range: -2.4723
Max Act: 1.8832. Min Act: -0.0001
Data Index: 120844 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4723. Min Range: -2.4723
Max Act: 1.4899. Min Act: -0.0000
Data Index: 528684 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4723. Min Range: -2.4723
Max Act: 1.7492. Min Act: -0.0001
Data Index: 612914 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4723. Min Range: -2.4723
Max Act: 1.8242. Min Act: -0.0001
Data Index: 319997 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4723. Min Range: -2.4723
Max Act: 1.7294. Min Act: -0.0001
Data Index: 1287544 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4723. Min Range: -2.4723
Max Act: 1.7285. Min Act: -0.0001
Data Index: 88132 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4723. Min Range: -2.4723
Max Act: 1.7096. Min Act: -0.0001
Data Index: 12663 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4723. Min Range: -2.4723
Max Act: 1.7115. Min Act: -0.0001
Data Index: 239068 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4723. Min Range: -2.4723
Max Act: 1.7050. Min Act: -0.0001
Data Index: 993397 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4723. Min Range: -2.4723
Max Act: 1.7387. Min Act: -0.0001
Data Index: 862013 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4723. Min Range: -2.4723
Max Act: 1.5916. Min Act: -0.0001
Data Index: 1258905 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19