Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3617 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.1236. Min Range: -0.1236
Max Act: 0.1236. Min Act: -0.0001
Data Index: 748527 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1236. Min Range: -0.1236
Max Act: 0.1061. Min Act: -0.0001
Data Index: 1149790 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1236. Min Range: -0.1236
Max Act: 0.0992. Min Act: -0.0001
Data Index: 319595 (C4 (Web Text))
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1236. Min Range: -0.1236
Max Act: 0.0993. Min Act: -0.0001
Data Index: 793281 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1236. Min Range: -0.1236
Max Act: 0.0974. Min Act: -0.0001
Data Index: 435351 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1236. Min Range: -0.1236
Max Act: 0.0927. Min Act: -0.0001
Data Index: 1272981 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1236. Min Range: -0.1236
Max Act: 0.0874. Min Act: -0.0001
Data Index: 515919 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1236. Min Range: -0.1236
Max Act: 0.0964. Min Act: -0.0001
Data Index: 207608 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1236. Min Range: -0.1236
Max Act: 0.0923. Min Act: -0.0001
Data Index: 1232511 (C4 (Web Text))
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1236. Min Range: -0.1236
Max Act: 0.0852. Min Act: -0.0001
Data Index: 1414229 (Python Code)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1236. Min Range: -0.1236
Max Act: 0.0900. Min Act: -0.0001
Data Index: 1464887 (Python Code)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1236. Min Range: -0.1236
Max Act: 0.0819. Min Act: -0.0001
Data Index: 879033 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1236. Min Range: -0.1236
Max Act: 0.0816. Min Act: -0.0001
Data Index: 633878 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1236. Min Range: -0.1236
Max Act: 0.0812. Min Act: -0.0001
Data Index: 288300 (C4 (Web Text))
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1236. Min Range: -0.1236
Max Act: 0.0795. Min Act: -0.0001
Data Index: 545935 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1236. Min Range: -0.1236
Max Act: 0.0813. Min Act: -0.0001
Data Index: 993349 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1236. Min Range: -0.1236
Max Act: 0.0810. Min Act: -0.0001
Data Index: 405281 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1236. Min Range: -0.1236
Max Act: 0.0763. Min Act: -0.0001
Data Index: 1078530 (C4 (Web Text))
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1236. Min Range: -0.1236
Max Act: 0.0775. Min Act: -0.0001
Data Index: 1265997 (C4 (Web Text))
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1236. Min Range: -0.1236
Max Act: 0.0802. Min Act: -0.0001
Data Index: 877 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19