Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3439 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.3268. Min Range: -2.3268
Max Act: 2.3268. Min Act: -0.0001
Data Index: 1123121 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3268. Min Range: -2.3268
Max Act: 2.1288. Min Act: -0.0001
Data Index: 481400 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3268. Min Range: -2.3268
Max Act: 2.1664. Min Act: -0.0001
Data Index: 31114 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3268. Min Range: -2.3268
Max Act: 1.9386. Min Act: -0.0001
Data Index: 1155462 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3268. Min Range: -2.3268
Max Act: 2.0358. Min Act: -0.0001
Data Index: 1269106 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3268. Min Range: -2.3268
Max Act: 2.1228. Min Act: -0.0001
Data Index: 1185044 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3268. Min Range: -2.3268
Max Act: 1.8991. Min Act: -0.0001
Data Index: 300718 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3268. Min Range: -2.3268
Max Act: 2.0228. Min Act: -0.0001
Data Index: 895377 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3268. Min Range: -2.3268
Max Act: 1.7957. Min Act: -0.0001
Data Index: 785292 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3268. Min Range: -2.3268
Max Act: 1.7978. Min Act: -0.0001
Data Index: 559484 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3268. Min Range: -2.3268
Max Act: 1.7929. Min Act: -0.0001
Data Index: 791622 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3268. Min Range: -2.3268
Max Act: 2.0017. Min Act: -0.0001
Data Index: 328684 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3268. Min Range: -2.3268
Max Act: 1.9029. Min Act: -0.0001
Data Index: 1197327 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3268. Min Range: -2.3268
Max Act: 1.8956. Min Act: -0.0001
Data Index: 1004629 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3268. Min Range: -2.3268
Max Act: 1.7814. Min Act: -0.0001
Data Index: 437401 (C4 (Web Text))
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3268. Min Range: -2.3268
Max Act: 1.7852. Min Act: -0.0001
Data Index: 766649 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3268. Min Range: -2.3268
Max Act: 1.8729. Min Act: -0.0001
Data Index: 745670 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3268. Min Range: -2.3268
Max Act: 1.9655. Min Act: -0.0001
Data Index: 1182029 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3268. Min Range: -2.3268
Max Act: 1.8670. Min Act: -0.0001
Data Index: 1216148 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3268. Min Range: -2.3268
Max Act: 1.8333. Min Act: -0.0001
Data Index: 733558 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19