Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3989 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.8241. Min Range: -2.8241
Max Act: 2.6327. Min Act: -0.0002
Data Index: 143797 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8241. Min Range: -2.8241
Max Act: 2.5775. Min Act: -0.0001
Data Index: 931666 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8241. Min Range: -2.8241
Max Act: 2.5658. Min Act: -0.0001
Data Index: 605144 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8241. Min Range: -2.8241
Max Act: 2.8241. Min Act: -0.0001
Data Index: 489869 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8241. Min Range: -2.8241
Max Act: 2.2401. Min Act: -0.0001
Data Index: 360418 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8241. Min Range: -2.8241
Max Act: 2.2195. Min Act: -0.0001
Data Index: 337705 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8241. Min Range: -2.8241
Max Act: 2.2973. Min Act: -0.0001
Data Index: 1030454 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8241. Min Range: -2.8241
Max Act: 2.0112. Min Act: -0.0001
Data Index: 1332016 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8241. Min Range: -2.8241
Max Act: 1.9015. Min Act: -0.0001
Data Index: 501839 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8241. Min Range: -2.8241
Max Act: 1.8845. Min Act: -0.0001
Data Index: 1024059 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8241. Min Range: -2.8241
Max Act: 1.8553. Min Act: -0.0001
Data Index: 611991 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8241. Min Range: -2.8241
Max Act: 1.7307. Min Act: -0.0001
Data Index: 1112209 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8241. Min Range: -2.8241
Max Act: 1.8147. Min Act: -0.0001
Data Index: 58868 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8241. Min Range: -2.8241
Max Act: 1.9970. Min Act: -0.0001
Data Index: 1147592 (C4 (Web Text))
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8241. Min Range: -2.8241
Max Act: 1.8515. Min Act: -0.0001
Data Index: 1322032 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8241. Min Range: -2.8241
Max Act: 1.7512. Min Act: -0.0001
Data Index: 28847 (C4 (Web Text))
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8241. Min Range: -2.8241
Max Act: 1.7678. Min Act: -0.0001
Data Index: 1358365 (C4 (Web Text))
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8241. Min Range: -2.8241
Max Act: 1.7887. Min Act: -0.0001
Data Index: 1030994 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8241. Min Range: -2.8241
Max Act: 1.7775. Min Act: -0.0001
Data Index: 952487 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8241. Min Range: -2.8241
Max Act: 1.9144. Min Act: -0.0001
Data Index: 911680 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #19