Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3221 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 3.6836. Min Range: -3.6836
Max Act: 3.6836. Min Act: -0.0001
Data Index: 549773 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6836. Min Range: -3.6836
Max Act: 3.1962. Min Act: -0.0001
Data Index: 101181 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6836. Min Range: -3.6836
Max Act: 2.9865. Min Act: -0.0001
Data Index: 848261 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6836. Min Range: -3.6836
Max Act: 3.2149. Min Act: -0.0001
Data Index: 782709 (C4 (Web Text))
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6836. Min Range: -3.6836
Max Act: 3.1240. Min Act: -0.0001
Data Index: 895328 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6836. Min Range: -3.6836
Max Act: 3.0931. Min Act: -0.0001
Data Index: 400787 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6836. Min Range: -3.6836
Max Act: 3.0534. Min Act: -0.0001
Data Index: 1329185 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6836. Min Range: -3.6836
Max Act: 3.0344. Min Act: -0.0001
Data Index: 771180 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6836. Min Range: -3.6836
Max Act: 3.1577. Min Act: -0.0001
Data Index: 681827 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6836. Min Range: -3.6836
Max Act: 2.8325. Min Act: -0.0001
Data Index: 917661 (C4 (Web Text))
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6836. Min Range: -3.6836
Max Act: 2.9955. Min Act: -0.0001
Data Index: 16375 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6836. Min Range: -3.6836
Max Act: 2.7277. Min Act: -0.0001
Data Index: 967528 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6836. Min Range: -3.6836
Max Act: 2.9968. Min Act: -0.0001
Data Index: 699050 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6836. Min Range: -3.6836
Max Act: 2.9617. Min Act: -0.0001
Data Index: 687467 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6836. Min Range: -3.6836
Max Act: 2.9022. Min Act: -0.0001
Data Index: 67238 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6836. Min Range: -3.6836
Max Act: 2.7545. Min Act: -0.0001
Data Index: 205830 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6836. Min Range: -3.6836
Max Act: 2.8918. Min Act: -0.0001
Data Index: 993127 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6836. Min Range: -3.6836
Max Act: 2.8927. Min Act: -0.0001
Data Index: 1026109 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6836. Min Range: -3.6836
Max Act: 2.6785. Min Act: -0.0001
Data Index: 1173416 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6836. Min Range: -3.6836
Max Act: 2.8191. Min Act: -0.0001
Data Index: 6194 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19