Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3083 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.1803. Min Range: -1.1803
Max Act: 1.1791. Min Act: -0.0001
Data Index: 824438 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1803. Min Range: -1.1803
Max Act: 1.1803. Min Act: -0.0001
Data Index: 671790 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1803. Min Range: -1.1803
Max Act: 1.0972. Min Act: -0.0001
Data Index: 821956 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1803. Min Range: -1.1803
Max Act: 1.0716. Min Act: -0.0001
Data Index: 516634 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1803. Min Range: -1.1803
Max Act: 1.0568. Min Act: -0.0001
Data Index: 725187 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1803. Min Range: -1.1803
Max Act: 1.0916. Min Act: -0.0001
Data Index: 62750 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1803. Min Range: -1.1803
Max Act: 1.0724. Min Act: -0.0001
Data Index: 10864 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1803. Min Range: -1.1803
Max Act: 1.0624. Min Act: -0.0001
Data Index: 368250 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1803. Min Range: -1.1803
Max Act: 1.0966. Min Act: -0.0001
Data Index: 912018 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1803. Min Range: -1.1803
Max Act: 1.0441. Min Act: -0.0001
Data Index: 155665 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1803. Min Range: -1.1803
Max Act: 1.0575. Min Act: -0.0001
Data Index: 480646 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1803. Min Range: -1.1803
Max Act: 0.9277. Min Act: -0.0001
Data Index: 256027 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1803. Min Range: -1.1803
Max Act: 1.0059. Min Act: -0.0001
Data Index: 592893 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1803. Min Range: -1.1803
Max Act: 1.0142. Min Act: -0.0001
Data Index: 664779 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1803. Min Range: -1.1803
Max Act: 0.9752. Min Act: -0.0001
Data Index: 17354 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1803. Min Range: -1.1803
Max Act: 0.9501. Min Act: -0.0001
Data Index: 194475 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1803. Min Range: -1.1803
Max Act: 0.9726. Min Act: -0.0001
Data Index: 551658 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1803. Min Range: -1.1803
Max Act: 0.9341. Min Act: -0.0001
Data Index: 769762 (C4 (Web Text))
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1803. Min Range: -1.1803
Max Act: 0.9284. Min Act: -0.0001
Data Index: 201997 (C4 (Web Text))
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1803. Min Range: -1.1803
Max Act: 0.9296. Min Act: -0.0001
Data Index: 563717 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19