Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3680 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.5699. Min Range: -0.5699
Max Act: 0.5699. Min Act: -0.0001
Data Index: 566015 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5699. Min Range: -0.5699
Max Act: 0.5103. Min Act: -0.0001
Data Index: 1156868 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5699. Min Range: -0.5699
Max Act: 0.5067. Min Act: -0.0001
Data Index: 86143 (C4 (Web Text))
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5699. Min Range: -0.5699
Max Act: 0.5142. Min Act: -0.0001
Data Index: 213204 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5699. Min Range: -0.5699
Max Act: 0.4705. Min Act: -0.0001
Data Index: 493204 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5699. Min Range: -0.5699
Max Act: 0.4405. Min Act: -0.0001
Data Index: 1100307 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5699. Min Range: -0.5699
Max Act: 0.4189. Min Act: -0.0001
Data Index: 1261216 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5699. Min Range: -0.5699
Max Act: 0.4621. Min Act: -0.0001
Data Index: 327881 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5699. Min Range: -0.5699
Max Act: 0.4707. Min Act: -0.0001
Data Index: 721768 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5699. Min Range: -0.5699
Max Act: 0.3873. Min Act: -0.0001
Data Index: 1207859 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5699. Min Range: -0.5699
Max Act: 0.4067. Min Act: -0.0001
Data Index: 527823 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5699. Min Range: -0.5699
Max Act: 0.4135. Min Act: -0.0001
Data Index: 142097 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5699. Min Range: -0.5699
Max Act: 0.3857. Min Act: -0.0001
Data Index: 107688 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5699. Min Range: -0.5699
Max Act: 0.3823. Min Act: -0.0001
Data Index: 1179675 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5699. Min Range: -0.5699
Max Act: 0.3988. Min Act: -0.0001
Data Index: 1178436 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5699. Min Range: -0.5699
Max Act: 0.3794. Min Act: -0.0001
Data Index: 892734 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5699. Min Range: -0.5699
Max Act: 0.4505. Min Act: -0.0001
Data Index: 677944 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5699. Min Range: -0.5699
Max Act: 0.3916. Min Act: -0.0001
Data Index: 346243 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5699. Min Range: -0.5699
Max Act: 0.4030. Min Act: -0.0001
Data Index: 1159471 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5699. Min Range: -0.5699
Max Act: 0.3747. Min Act: -0.0001
Data Index: 1179084 (C4 (Web Text))
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19