Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2903 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.3275. Min Range: -2.3275
Max Act: 2.3275. Min Act: -0.0001
Data Index: 690637 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3275. Min Range: -2.3275
Max Act: 2.1463. Min Act: -0.0001
Data Index: 883808 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3275. Min Range: -2.3275
Max Act: 2.1313. Min Act: -0.0001
Data Index: 75322 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3275. Min Range: -2.3275
Max Act: 2.2075. Min Act: -0.0001
Data Index: 529976 (C4 (Web Text))
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3275. Min Range: -2.3275
Max Act: 2.0685. Min Act: -0.0001
Data Index: 1247438 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3275. Min Range: -2.3275
Max Act: 2.0796. Min Act: -0.0001
Data Index: 724433 (C4 (Web Text))
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3275. Min Range: -2.3275
Max Act: 1.9595. Min Act: -0.0001
Data Index: 560326 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3275. Min Range: -2.3275
Max Act: 1.7836. Min Act: -0.0001
Data Index: 1293508 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3275. Min Range: -2.3275
Max Act: 2.0479. Min Act: -0.0001
Data Index: 183873 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3275. Min Range: -2.3275
Max Act: 1.8190. Min Act: -0.0001
Data Index: 303951 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3275. Min Range: -2.3275
Max Act: 1.8381. Min Act: -0.0001
Data Index: 1120033 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3275. Min Range: -2.3275
Max Act: 1.8231. Min Act: -0.0001
Data Index: 79322 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3275. Min Range: -2.3275
Max Act: 1.8694. Min Act: -0.0001
Data Index: 398808 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3275. Min Range: -2.3275
Max Act: 1.8076. Min Act: -0.0001
Data Index: 988366 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3275. Min Range: -2.3275
Max Act: 1.8741. Min Act: -0.0001
Data Index: 917799 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3275. Min Range: -2.3275
Max Act: 1.7417. Min Act: -0.0001
Data Index: 486668 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3275. Min Range: -2.3275
Max Act: 1.8533. Min Act: -0.0001
Data Index: 1153900 (C4 (Web Text))
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3275. Min Range: -2.3275
Max Act: 1.7488. Min Act: -0.0001
Data Index: 1036685 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3275. Min Range: -2.3275
Max Act: 1.8127. Min Act: -0.0001
Data Index: 649804 (C4 (Web Text))
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3275. Min Range: -2.3275
Max Act: 1.7917. Min Act: -0.0001
Data Index: 501906 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19