Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4122 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.5986. Min Range: -2.5986
Max Act: 2.5986. Min Act: -0.0001
Data Index: 604109 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5986. Min Range: -2.5986
Max Act: 2.4274. Min Act: -0.0001
Data Index: 633884 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5986. Min Range: -2.5986
Max Act: 2.1821. Min Act: -0.0001
Data Index: 228905 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5986. Min Range: -2.5986
Max Act: 1.8660. Min Act: -0.0001
Data Index: 167948 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5986. Min Range: -2.5986
Max Act: 1.9495. Min Act: -0.0001
Data Index: 671183 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5986. Min Range: -2.5986
Max Act: 1.9933. Min Act: -0.0001
Data Index: 934773 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5986. Min Range: -2.5986
Max Act: 1.7280. Min Act: -0.0001
Data Index: 68951 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5986. Min Range: -2.5986
Max Act: 1.7976. Min Act: -0.0001
Data Index: 1251000 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5986. Min Range: -2.5986
Max Act: 1.8177. Min Act: -0.0001
Data Index: 1040501 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5986. Min Range: -2.5986
Max Act: 1.7867. Min Act: -0.0001
Data Index: 418362 (C4 (Web Text))
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5986. Min Range: -2.5986
Max Act: 1.7028. Min Act: -0.0001
Data Index: 979872 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5986. Min Range: -2.5986
Max Act: 1.6193. Min Act: -0.0001
Data Index: 935511 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5986. Min Range: -2.5986
Max Act: 1.8568. Min Act: -0.0001
Data Index: 824626 (C4 (Web Text))
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5986. Min Range: -2.5986
Max Act: 1.7791. Min Act: -0.0001
Data Index: 70745 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5986. Min Range: -2.5986
Max Act: 1.7257. Min Act: -0.0001
Data Index: 128051 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5986. Min Range: -2.5986
Max Act: 1.7303. Min Act: -0.0001
Data Index: 484325 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5986. Min Range: -2.5986
Max Act: 1.8544. Min Act: -0.0001
Data Index: 315904 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5986. Min Range: -2.5986
Max Act: 1.5183. Min Act: -0.0001
Data Index: 109546 (C4 (Web Text))
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5986. Min Range: -2.5986
Max Act: 1.4967. Min Act: -0.0001
Data Index: 518383 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5986. Min Range: -2.5986
Max Act: 1.5599. Min Act: -0.0001
Data Index: 750 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19