Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2918 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.0755. Min Range: -1.0755
Max Act: 1.0755. Min Act: -0.0001
Data Index: 42394 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0755. Min Range: -1.0755
Max Act: 1.0224. Min Act: -0.0001
Data Index: 459976 (C4 (Web Text))
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0755. Min Range: -1.0755
Max Act: 0.8567. Min Act: -0.0001
Data Index: 30545 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0755. Min Range: -1.0755
Max Act: 0.9085. Min Act: -0.0001
Data Index: 873447 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0755. Min Range: -1.0755
Max Act: 0.9360. Min Act: -0.0001
Data Index: 172560 (C4 (Web Text))
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0755. Min Range: -1.0755
Max Act: 0.8700. Min Act: -0.0001
Data Index: 146462 (C4 (Web Text))
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0755. Min Range: -1.0755
Max Act: 0.8443. Min Act: -0.0001
Data Index: 430642 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0755. Min Range: -1.0755
Max Act: 0.8782. Min Act: -0.0001
Data Index: 1125598 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0755. Min Range: -1.0755
Max Act: 0.8457. Min Act: -0.0001
Data Index: 1068432 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0755. Min Range: -1.0755
Max Act: 0.8476. Min Act: -0.0001
Data Index: 1309206 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0755. Min Range: -1.0755
Max Act: 0.8649. Min Act: -0.0001
Data Index: 1029723 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0755. Min Range: -1.0755
Max Act: 0.8269. Min Act: -0.0001
Data Index: 1149697 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0755. Min Range: -1.0755
Max Act: 0.8298. Min Act: -0.0001
Data Index: 893120 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0755. Min Range: -1.0755
Max Act: 0.8264. Min Act: -0.0001
Data Index: 398459 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0755. Min Range: -1.0755
Max Act: 0.8490. Min Act: -0.0001
Data Index: 284939 (C4 (Web Text))
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0755. Min Range: -1.0755
Max Act: 0.8171. Min Act: -0.0001
Data Index: 1323259 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0755. Min Range: -1.0755
Max Act: 0.8087. Min Act: -0.0001
Data Index: 709180 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0755. Min Range: -1.0755
Max Act: 0.8142. Min Act: -0.0001
Data Index: 208386 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0755. Min Range: -1.0755
Max Act: 0.7913. Min Act: -0.0001
Data Index: 810529 (C4 (Web Text))
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0755. Min Range: -1.0755
Max Act: 0.7956. Min Act: -0.0001
Data Index: 434755 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19