Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1882 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.2405. Min Range: -2.2405
Max Act: 2.2405. Min Act: -0.0001
Data Index: 513843 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2405. Min Range: -2.2405
Max Act: 2.0442. Min Act: -0.0001
Data Index: 864600 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2405. Min Range: -2.2405
Max Act: 1.9275. Min Act: -0.0001
Data Index: 271730 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2405. Min Range: -2.2405
Max Act: 2.0530. Min Act: -0.0001
Data Index: 1386570 (Python Code)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2405. Min Range: -2.2405
Max Act: 1.8673. Min Act: -0.0001
Data Index: 29064 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2405. Min Range: -2.2405
Max Act: 1.8435. Min Act: -0.0001
Data Index: 1451440 (Python Code)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2405. Min Range: -2.2405
Max Act: 1.8301. Min Act: -0.0001
Data Index: 98648 (C4 (Web Text))
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2405. Min Range: -2.2405
Max Act: 1.7606. Min Act: -0.0001
Data Index: 1462114 (Python Code)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2405. Min Range: -2.2405
Max Act: 1.8617. Min Act: -0.0001
Data Index: 282380 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2405. Min Range: -2.2405
Max Act: 1.7528. Min Act: -0.0001
Data Index: 1600150 (Python Code)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2405. Min Range: -2.2405
Max Act: 1.7519. Min Act: -0.0001
Data Index: 769013 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2405. Min Range: -2.2405
Max Act: 1.7351. Min Act: -0.0001
Data Index: 1211965 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2405. Min Range: -2.2405
Max Act: 1.7280. Min Act: -0.0001
Data Index: 44820 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2405. Min Range: -2.2405
Max Act: 1.6964. Min Act: -0.0001
Data Index: 863035 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2405. Min Range: -2.2405
Max Act: 1.5025. Min Act: -0.0001
Data Index: 523398 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2405. Min Range: -2.2405
Max Act: 1.6683. Min Act: -0.0001
Data Index: 817798 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2405. Min Range: -2.2405
Max Act: 1.6525. Min Act: -0.0001
Data Index: 1324821 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2405. Min Range: -2.2405
Max Act: 1.6157. Min Act: -0.0001
Data Index: 895451 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2405. Min Range: -2.2405
Max Act: 1.5020. Min Act: -0.0001
Data Index: 758674 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2405. Min Range: -2.2405
Max Act: 1.4951. Min Act: -0.0001
Data Index: 1522119 (Python Code)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19