Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 638 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.6580. Min Range: -1.6580
Max Act: 1.6580. Min Act: -0.0001
Data Index: 381036 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6580. Min Range: -1.6580
Max Act: 1.5528. Min Act: -0.0001
Data Index: 301691 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6580. Min Range: -1.6580
Max Act: 1.4378. Min Act: -0.0001
Data Index: 320285 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6580. Min Range: -1.6580
Max Act: 1.4171. Min Act: -0.0001
Data Index: 990448 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6580. Min Range: -1.6580
Max Act: 1.5773. Min Act: -0.0001
Data Index: 764563 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6580. Min Range: -1.6580
Max Act: 1.3766. Min Act: -0.0001
Data Index: 136772 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6580. Min Range: -1.6580
Max Act: 1.2925. Min Act: -0.0001
Data Index: 1303994 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6580. Min Range: -1.6580
Max Act: 1.2558. Min Act: -0.0001
Data Index: 853685 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6580. Min Range: -1.6580
Max Act: 1.2692. Min Act: -0.0001
Data Index: 1154922 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6580. Min Range: -1.6580
Max Act: 1.3330. Min Act: -0.0001
Data Index: 491001 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6580. Min Range: -1.6580
Max Act: 1.3838. Min Act: -0.0001
Data Index: 1344095 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6580. Min Range: -1.6580
Max Act: 1.3281. Min Act: -0.0001
Data Index: 1248464 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6580. Min Range: -1.6580
Max Act: 1.2674. Min Act: -0.0001
Data Index: 895229 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6580. Min Range: -1.6580
Max Act: 1.3424. Min Act: -0.0001
Data Index: 385343 (C4 (Web Text))
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6580. Min Range: -1.6580
Max Act: 1.2962. Min Act: -0.0001
Data Index: 681252 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6580. Min Range: -1.6580
Max Act: 1.0811. Min Act: -0.0001
Data Index: 179001 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6580. Min Range: -1.6580
Max Act: 1.2197. Min Act: -0.0001
Data Index: 521592 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6580. Min Range: -1.6580
Max Act: 1.1576. Min Act: -0.0001
Data Index: 406038 (C4 (Web Text))
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6580. Min Range: -1.6580
Max Act: 1.2774. Min Act: -0.0001
Data Index: 208581 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6580. Min Range: -1.6580
Max Act: 1.1143. Min Act: -0.0001
Data Index: 1317984 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19