Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3878 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.0926. Min Range: -2.0926
Max Act: 2.0926. Min Act: -0.0000
Data Index: 1245867 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0926. Min Range: -2.0926
Max Act: 2.0140. Min Act: -0.0001
Data Index: 288217 (C4 (Web Text))
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0926. Min Range: -2.0926
Max Act: 1.9329. Min Act: -0.0001
Data Index: 1344946 (C4 (Web Text))
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0926. Min Range: -2.0926
Max Act: 1.7508. Min Act: -0.0001
Data Index: 1007500 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0926. Min Range: -2.0926
Max Act: 1.6474. Min Act: -0.0001
Data Index: 73847 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0926. Min Range: -2.0926
Max Act: 1.8393. Min Act: -0.0001
Data Index: 1137522 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0926. Min Range: -2.0926
Max Act: 1.5645. Min Act: -0.0001
Data Index: 921717 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0926. Min Range: -2.0926
Max Act: 1.6224. Min Act: -0.0000
Data Index: 83768 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0926. Min Range: -2.0926
Max Act: 1.6261. Min Act: -0.0001
Data Index: 1064557 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0926. Min Range: -2.0926
Max Act: 1.5150. Min Act: -0.0000
Data Index: 29145 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0926. Min Range: -2.0926
Max Act: 1.6061. Min Act: -0.0001
Data Index: 1341221 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0926. Min Range: -2.0926
Max Act: 1.5944. Min Act: -0.0000
Data Index: 368214 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0926. Min Range: -2.0926
Max Act: 1.4694. Min Act: -0.0001
Data Index: 435005 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0926. Min Range: -2.0926
Max Act: 1.4767. Min Act: -0.0001
Data Index: 1166509 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0926. Min Range: -2.0926
Max Act: 1.5715. Min Act: -0.0001
Data Index: 481818 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0926. Min Range: -2.0926
Max Act: 1.5149. Min Act: -0.0001
Data Index: 1349705 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0926. Min Range: -2.0926
Max Act: 1.5237. Min Act: -0.0001
Data Index: 367633 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0926. Min Range: -2.0926
Max Act: 1.3607. Min Act: -0.0000
Data Index: 3954 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0926. Min Range: -2.0926
Max Act: 1.5006. Min Act: -0.0001
Data Index: 373203 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0926. Min Range: -2.0926
Max Act: 1.5851. Min Act: -0.0001
Data Index: 665809 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19