Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2879 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.6033. Min Range: -2.6033
Max Act: 2.6033. Min Act: -0.0001
Data Index: 872951 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6033. Min Range: -2.6033
Max Act: 1.6043. Min Act: -0.0001
Data Index: 258238 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6033. Min Range: -2.6033
Max Act: 1.8023. Min Act: -0.0001
Data Index: 565753 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6033. Min Range: -2.6033
Max Act: 1.5945. Min Act: -0.0001
Data Index: 940216 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6033. Min Range: -2.6033
Max Act: 1.5665. Min Act: -0.0001
Data Index: 484206 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6033. Min Range: -2.6033
Max Act: 1.5940. Min Act: -0.0001
Data Index: 652013 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6033. Min Range: -2.6033
Max Act: 1.3425. Min Act: -0.0000
Data Index: 1008319 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6033. Min Range: -2.6033
Max Act: 1.3225. Min Act: -0.0001
Data Index: 334722 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6033. Min Range: -2.6033
Max Act: 1.3013. Min Act: -0.0001
Data Index: 1001147 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6033. Min Range: -2.6033
Max Act: 1.2908. Min Act: -0.0001
Data Index: 283190 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6033. Min Range: -2.6033
Max Act: 1.3188. Min Act: -0.0001
Data Index: 277209 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6033. Min Range: -2.6033
Max Act: 1.1487. Min Act: -0.0001
Data Index: 578005 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6033. Min Range: -2.6033
Max Act: 1.8350. Min Act: -0.0001
Data Index: 477373 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6033. Min Range: -2.6033
Max Act: 1.2417. Min Act: -0.0001
Data Index: 465964 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6033. Min Range: -2.6033
Max Act: 1.3248. Min Act: -0.0001
Data Index: 283689 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6033. Min Range: -2.6033
Max Act: 1.1692. Min Act: -0.0001
Data Index: 1055967 (C4 (Web Text))
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6033. Min Range: -2.6033
Max Act: 1.1827. Min Act: -0.0001
Data Index: 668887 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6033. Min Range: -2.6033
Max Act: 1.2171. Min Act: -0.0001
Data Index: 787726 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6033. Min Range: -2.6033
Max Act: 1.2891. Min Act: -0.0000
Data Index: 1031042 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6033. Min Range: -2.6033
Max Act: 0.9360. Min Act: -0.0001
Data Index: 781809 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19