Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4221 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.7270. Min Range: -2.7270
Max Act: 2.5109. Min Act: -0.0001
Data Index: 1078783 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7270. Min Range: -2.7270
Max Act: 2.7270. Min Act: -0.0001
Data Index: 87117 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7270. Min Range: -2.7270
Max Act: 2.6895. Min Act: -0.0001
Data Index: 606163 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7270. Min Range: -2.7270
Max Act: 2.5171. Min Act: -0.0001
Data Index: 440832 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7270. Min Range: -2.7270
Max Act: 2.5927. Min Act: -0.0001
Data Index: 411991 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7270. Min Range: -2.7270
Max Act: 2.3971. Min Act: -0.0001
Data Index: 154589 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7270. Min Range: -2.7270
Max Act: 2.2241. Min Act: -0.0001
Data Index: 425410 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7270. Min Range: -2.7270
Max Act: 2.4657. Min Act: -0.0001
Data Index: 1249420 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7270. Min Range: -2.7270
Max Act: 1.6839. Min Act: -0.0001
Data Index: 139309 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7270. Min Range: -2.7270
Max Act: 2.1921. Min Act: -0.0001
Data Index: 403967 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7270. Min Range: -2.7270
Max Act: 2.3883. Min Act: -0.0001
Data Index: 633985 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7270. Min Range: -2.7270
Max Act: 2.2449. Min Act: -0.0001
Data Index: 1189497 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7270. Min Range: -2.7270
Max Act: 2.1310. Min Act: -0.0001
Data Index: 570131 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7270. Min Range: -2.7270
Max Act: 2.0123. Min Act: -0.0001
Data Index: 269923 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7270. Min Range: -2.7270
Max Act: 1.9721. Min Act: -0.0001
Data Index: 506311 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7270. Min Range: -2.7270
Max Act: 2.1186. Min Act: -0.0001
Data Index: 1152358 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7270. Min Range: -2.7270
Max Act: 2.0691. Min Act: -0.0001
Data Index: 401560 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7270. Min Range: -2.7270
Max Act: 2.1076. Min Act: -0.0001
Data Index: 1319638 (C4 (Web Text))
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7270. Min Range: -2.7270
Max Act: 1.9510. Min Act: -0.0001
Data Index: 127260 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7270. Min Range: -2.7270
Max Act: 2.0914. Min Act: -0.0001
Data Index: 782760 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19