Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 516 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.0661. Min Range: -2.0661
Max Act: 2.0661. Min Act: -0.0001
Data Index: 606528 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0661. Min Range: -2.0661
Max Act: 2.0561. Min Act: -0.0001
Data Index: 1267080 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0661. Min Range: -2.0661
Max Act: 1.7466. Min Act: -0.0001
Data Index: 664958 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0661. Min Range: -2.0661
Max Act: 1.7230. Min Act: -0.0001
Data Index: 409954 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0661. Min Range: -2.0661
Max Act: 1.7241. Min Act: -0.0001
Data Index: 1104206 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0661. Min Range: -2.0661
Max Act: 1.8165. Min Act: -0.0001
Data Index: 175426 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0661. Min Range: -2.0661
Max Act: 1.5750. Min Act: -0.0001
Data Index: 1096928 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0661. Min Range: -2.0661
Max Act: 1.5308. Min Act: -0.0001
Data Index: 31390 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0661. Min Range: -2.0661
Max Act: 1.5343. Min Act: -0.0001
Data Index: 1360674 (Python Code)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0661. Min Range: -2.0661
Max Act: 1.6648. Min Act: -0.0001
Data Index: 174622 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0661. Min Range: -2.0661
Max Act: 1.5058. Min Act: -0.0001
Data Index: 595229 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0661. Min Range: -2.0661
Max Act: 1.5374. Min Act: -0.0001
Data Index: 456580 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0661. Min Range: -2.0661
Max Act: 1.4518. Min Act: -0.0001
Data Index: 1650244 (Python Code)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0661. Min Range: -2.0661
Max Act: 1.4743. Min Act: -0.0001
Data Index: 1074871 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0661. Min Range: -2.0661
Max Act: 1.4752. Min Act: -0.0001
Data Index: 1161976 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0661. Min Range: -2.0661
Max Act: 1.4371. Min Act: -0.0001
Data Index: 927456 (C4 (Web Text))
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0661. Min Range: -2.0661
Max Act: 1.4903. Min Act: -0.0001
Data Index: 681207 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0661. Min Range: -2.0661
Max Act: 1.5194. Min Act: -0.0001
Data Index: 442259 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0661. Min Range: -2.0661
Max Act: 1.5513. Min Act: -0.0001
Data Index: 189249 (C4 (Web Text))
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0661. Min Range: -2.0661
Max Act: 1.5317. Min Act: -0.0001
Data Index: 1011249 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #19