Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3723 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 3.6312. Min Range: -3.6312
Max Act: 3.6312. Min Act: -0.0001
Data Index: 223816 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6312. Min Range: -3.6312
Max Act: 2.9015. Min Act: -0.0001
Data Index: 1201210 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6312. Min Range: -3.6312
Max Act: 2.5882. Min Act: -0.0001
Data Index: 724013 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6312. Min Range: -3.6312
Max Act: 2.3456. Min Act: -0.0001
Data Index: 1375877 (Python Code)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6312. Min Range: -3.6312
Max Act: 2.2794. Min Act: -0.0001
Data Index: 1046822 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6312. Min Range: -3.6312
Max Act: 1.9374. Min Act: -0.0001
Data Index: 1613998 (Python Code)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6312. Min Range: -3.6312
Max Act: 2.2254. Min Act: -0.0001
Data Index: 1458869 (Python Code)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6312. Min Range: -3.6312
Max Act: 1.9935. Min Act: -0.0001
Data Index: 1646933 (Python Code)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6312. Min Range: -3.6312
Max Act: 2.2112. Min Act: -0.0001
Data Index: 1569204 (Python Code)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6312. Min Range: -3.6312
Max Act: 2.4486. Min Act: -0.0001
Data Index: 1438886 (Python Code)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6312. Min Range: -3.6312
Max Act: 1.9642. Min Act: -0.0001
Data Index: 1376992 (Python Code)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6312. Min Range: -3.6312
Max Act: 2.1327. Min Act: -0.0001
Data Index: 1654468 (Python Code)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6312. Min Range: -3.6312
Max Act: 2.1350. Min Act: -0.0001
Data Index: 1497191 (Python Code)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6312. Min Range: -3.6312
Max Act: 1.9065. Min Act: -0.0001
Data Index: 1614944 (Python Code)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6312. Min Range: -3.6312
Max Act: 2.2459. Min Act: -0.0001
Data Index: 1403378 (Python Code)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6312. Min Range: -3.6312
Max Act: 2.1183. Min Act: -0.0001
Data Index: 1572931 (Python Code)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6312. Min Range: -3.6312
Max Act: 2.1294. Min Act: -0.0001
Data Index: 1506853 (Python Code)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6312. Min Range: -3.6312
Max Act: 2.1053. Min Act: -0.0001
Data Index: 27252 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6312. Min Range: -3.6312
Max Act: 2.2157. Min Act: -0.0001
Data Index: 1407443 (Python Code)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6312. Min Range: -3.6312
Max Act: 2.0821. Min Act: -0.0001
Data Index: 1312131 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19