Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3335 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.0750. Min Range: -2.0750
Max Act: 1.9474. Min Act: -0.0001
Data Index: 146522 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0750. Min Range: -2.0750
Max Act: 1.8234. Min Act: -0.0001
Data Index: 1170315 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0750. Min Range: -2.0750
Max Act: 2.0041. Min Act: -0.0001
Data Index: 359314 (C4 (Web Text))
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0750. Min Range: -2.0750
Max Act: 1.8873. Min Act: -0.0001
Data Index: 1274859 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0750. Min Range: -2.0750
Max Act: 2.0750. Min Act: -0.0001
Data Index: 1132680 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0750. Min Range: -2.0750
Max Act: 1.6736. Min Act: -0.0001
Data Index: 463392 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0750. Min Range: -2.0750
Max Act: 1.6785. Min Act: -0.0001
Data Index: 1271162 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0750. Min Range: -2.0750
Max Act: 1.6553. Min Act: -0.0001
Data Index: 492688 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0750. Min Range: -2.0750
Max Act: 1.7382. Min Act: -0.0001
Data Index: 251233 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0750. Min Range: -2.0750
Max Act: 1.7171. Min Act: -0.0001
Data Index: 274596 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0750. Min Range: -2.0750
Max Act: 1.7280. Min Act: -0.0001
Data Index: 695379 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0750. Min Range: -2.0750
Max Act: 1.8095. Min Act: -0.0001
Data Index: 98665 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0750. Min Range: -2.0750
Max Act: 1.6230. Min Act: -0.0001
Data Index: 138853 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0750. Min Range: -2.0750
Max Act: 1.7951. Min Act: -0.0001
Data Index: 1258044 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0750. Min Range: -2.0750
Max Act: 1.5997. Min Act: -0.0001
Data Index: 790434 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0750. Min Range: -2.0750
Max Act: 1.6865. Min Act: -0.0001
Data Index: 1299105 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0750. Min Range: -2.0750
Max Act: 1.6782. Min Act: -0.0001
Data Index: 569415 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0750. Min Range: -2.0750
Max Act: 1.5719. Min Act: -0.0001
Data Index: 1087210 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0750. Min Range: -2.0750
Max Act: 1.6561. Min Act: -0.0001
Data Index: 1309263 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0750. Min Range: -2.0750
Max Act: 1.5772. Min Act: -0.0001
Data Index: 222676 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19