Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2320 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.7217. Min Range: -0.7217
Max Act: 0.7217. Min Act: -0.0001
Data Index: 1443218 (Python Code)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7217. Min Range: -0.7217
Max Act: 0.7141. Min Act: -0.0001
Data Index: 1213779 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7217. Min Range: -0.7217
Max Act: 0.7119. Min Act: -0.0001
Data Index: 1586709 (Python Code)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7217. Min Range: -0.7217
Max Act: 0.7152. Min Act: -0.0001
Data Index: 1500024 (Python Code)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7217. Min Range: -0.7217
Max Act: 0.7003. Min Act: -0.0001
Data Index: 1639611 (Python Code)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7217. Min Range: -0.7217
Max Act: 0.6983. Min Act: -0.0001
Data Index: 1375503 (Python Code)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7217. Min Range: -0.7217
Max Act: 0.7109. Min Act: -0.0001
Data Index: 1382316 (Python Code)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7217. Min Range: -0.7217
Max Act: 0.6341. Min Act: -0.0001
Data Index: 1363900 (Python Code)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7217. Min Range: -0.7217
Max Act: 0.6197. Min Act: -0.0001
Data Index: 1626727 (Python Code)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7217. Min Range: -0.7217
Max Act: 0.6993. Min Act: -0.0001
Data Index: 1562812 (Python Code)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7217. Min Range: -0.7217
Max Act: 0.5944. Min Act: -0.0001
Data Index: 955327 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7217. Min Range: -0.7217
Max Act: 0.6119. Min Act: -0.0001
Data Index: 1536532 (Python Code)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7217. Min Range: -0.7217
Max Act: 0.6060. Min Act: -0.0001
Data Index: 1558618 (Python Code)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7217. Min Range: -0.7217
Max Act: 0.6019. Min Act: -0.0001
Data Index: 1438547 (Python Code)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7217. Min Range: -0.7217
Max Act: 0.5749. Min Act: -0.0001
Data Index: 1566771 (Python Code)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7217. Min Range: -0.7217
Max Act: 0.5551. Min Act: -0.0001
Data Index: 1498874 (Python Code)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7217. Min Range: -0.7217
Max Act: 0.5669. Min Act: -0.0001
Data Index: 1500909 (Python Code)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7217. Min Range: -0.7217
Max Act: 0.5776. Min Act: -0.0001
Data Index: 1396059 (Python Code)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7217. Min Range: -0.7217
Max Act: 0.5778. Min Act: -0.0001
Data Index: 1552238 (Python Code)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7217. Min Range: -0.7217
Max Act: 0.5507. Min Act: -0.0001
Data Index: 1468988 (Python Code)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19