Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4777 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 3.2998. Min Range: -3.2998
Max Act: 3.2998. Min Act: -0.0001
Data Index: 176994 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2998. Min Range: -3.2998
Max Act: 2.7907. Min Act: -0.0001
Data Index: 879597 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2998. Min Range: -3.2998
Max Act: 2.7241. Min Act: -0.0001
Data Index: 792183 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2998. Min Range: -3.2998
Max Act: 2.9378. Min Act: -0.0001
Data Index: 758534 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2998. Min Range: -3.2998
Max Act: 2.6048. Min Act: -0.0001
Data Index: 234204 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2998. Min Range: -3.2998
Max Act: 3.2503. Min Act: -0.0001
Data Index: 1072298 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2998. Min Range: -3.2998
Max Act: 2.4891. Min Act: -0.0001
Data Index: 307138 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2998. Min Range: -3.2998
Max Act: 2.3374. Min Act: -0.0001
Data Index: 958790 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2998. Min Range: -3.2998
Max Act: 2.4865. Min Act: -0.0001
Data Index: 759757 (C4 (Web Text))
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2998. Min Range: -3.2998
Max Act: 2.4889. Min Act: -0.0001
Data Index: 200299 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2998. Min Range: -3.2998
Max Act: 2.4961. Min Act: -0.0001
Data Index: 924442 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2998. Min Range: -3.2998
Max Act: 2.3788. Min Act: -0.0001
Data Index: 1184316 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2998. Min Range: -3.2998
Max Act: 2.2190. Min Act: -0.0001
Data Index: 1200859 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2998. Min Range: -3.2998
Max Act: 2.4444. Min Act: -0.0001
Data Index: 1616016 (Python Code)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2998. Min Range: -3.2998
Max Act: 2.5421. Min Act: -0.0001
Data Index: 654895 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2998. Min Range: -3.2998
Max Act: 2.5021. Min Act: -0.0001
Data Index: 1112644 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2998. Min Range: -3.2998
Max Act: 2.6479. Min Act: -0.0001
Data Index: 966311 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2998. Min Range: -3.2998
Max Act: 2.5371. Min Act: -0.0001
Data Index: 524296 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2998. Min Range: -3.2998
Max Act: 2.5107. Min Act: -0.0001
Data Index: 923873 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2998. Min Range: -3.2998
Max Act: 2.4751. Min Act: -0.0001
Data Index: 203332 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19