Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4221 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.0156. Min Range: -0.0156
Max Act: 0.0156. Min Act: -0.0001
Data Index: 304030 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0156. Min Range: -0.0156
Max Act: 0.0132. Min Act: -0.0001
Data Index: 609815 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0156. Min Range: -0.0156
Max Act: 0.0138. Min Act: -0.0001
Data Index: 1064323 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0156. Min Range: -0.0156
Max Act: 0.0104. Min Act: -0.0001
Data Index: 1087592 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0156. Min Range: -0.0156
Max Act: 0.0130. Min Act: -0.0001
Data Index: 585271 (C4 (Web Text))
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0156. Min Range: -0.0156
Max Act: 0.0130. Min Act: -0.0001
Data Index: 368699 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0156. Min Range: -0.0156
Max Act: 0.0127. Min Act: -0.0001
Data Index: 899533 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0156. Min Range: -0.0156
Max Act: 0.0132. Min Act: -0.0001
Data Index: 67451 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0156. Min Range: -0.0156
Max Act: 0.0107. Min Act: -0.0001
Data Index: 1621341 (Python Code)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0156. Min Range: -0.0156
Max Act: 0.0112. Min Act: -0.0001
Data Index: 1607369 (Python Code)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0156. Min Range: -0.0156
Max Act: 0.0117. Min Act: -0.0001
Data Index: 674938 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0156. Min Range: -0.0156
Max Act: 0.0111. Min Act: -0.0001
Data Index: 1010101 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0156. Min Range: -0.0156
Max Act: 0.0108. Min Act: -0.0001
Data Index: 1585376 (Python Code)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0156. Min Range: -0.0156
Max Act: 0.0107. Min Act: -0.0001
Data Index: 1482729 (Python Code)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0156. Min Range: -0.0156
Max Act: 0.0114. Min Act: -0.0001
Data Index: 1429948 (Python Code)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0156. Min Range: -0.0156
Max Act: 0.0096. Min Act: -0.0001
Data Index: 1032118 (C4 (Web Text))
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0156. Min Range: -0.0156
Max Act: 0.0106. Min Act: -0.0001
Data Index: 1206494 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0156. Min Range: -0.0156
Max Act: 0.0099. Min Act: -0.0001
Data Index: 1272109 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0156. Min Range: -0.0156
Max Act: 0.0109. Min Act: -0.0001
Data Index: 141384 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0156. Min Range: -0.0156
Max Act: 0.0109. Min Act: -0.0001
Data Index: 1112394 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19