Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3199 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.1281. Min Range: -0.1281
Max Act: 0.1281. Min Act: -0.0002
Data Index: 57659 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1281. Min Range: -0.1281
Max Act: 0.1214. Min Act: -0.0001
Data Index: 906437 (C4 (Web Text))
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1281. Min Range: -0.1281
Max Act: 0.1062. Min Act: -0.0001
Data Index: 786112 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1281. Min Range: -0.1281
Max Act: 0.1070. Min Act: -0.0001
Data Index: 1179446 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1281. Min Range: -0.1281
Max Act: 0.0945. Min Act: -0.0001
Data Index: 1114413 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1281. Min Range: -0.1281
Max Act: 0.1041. Min Act: -0.0001
Data Index: 982276 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1281. Min Range: -0.1281
Max Act: 0.1025. Min Act: -0.0001
Data Index: 412063 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1281. Min Range: -0.1281
Max Act: 0.1031. Min Act: -0.0001
Data Index: 3449 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1281. Min Range: -0.1281
Max Act: 0.0922. Min Act: -0.0001
Data Index: 1250601 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1281. Min Range: -0.1281
Max Act: 0.1011. Min Act: -0.0001
Data Index: 1123377 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1281. Min Range: -0.1281
Max Act: 0.1019. Min Act: -0.0001
Data Index: 413765 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1281. Min Range: -0.1281
Max Act: 0.1001. Min Act: -0.0001
Data Index: 333844 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1281. Min Range: -0.1281
Max Act: 0.0965. Min Act: -0.0001
Data Index: 911139 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1281. Min Range: -0.1281
Max Act: 0.0960. Min Act: -0.0001
Data Index: 853917 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1281. Min Range: -0.1281
Max Act: 0.0966. Min Act: -0.0001
Data Index: 1097780 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1281. Min Range: -0.1281
Max Act: 0.1003. Min Act: -0.0001
Data Index: 580421 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1281. Min Range: -0.1281
Max Act: 0.0966. Min Act: -0.0001
Data Index: 710395 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1281. Min Range: -0.1281
Max Act: 0.0941. Min Act: -0.0001
Data Index: 514463 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1281. Min Range: -0.1281
Max Act: 0.0962. Min Act: -0.0001
Data Index: 810332 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1281. Min Range: -0.1281
Max Act: 0.0970. Min Act: -0.0001
Data Index: 1070742 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #19