Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5181 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.9237. Min Range: -1.9237
Max Act: 1.9237. Min Act: -0.0001
Data Index: 778843 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9237. Min Range: -1.9237
Max Act: 1.5219. Min Act: -0.0001
Data Index: 495360 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9237. Min Range: -1.9237
Max Act: 1.5341. Min Act: -0.0001
Data Index: 776877 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9237. Min Range: -1.9237
Max Act: 1.3487. Min Act: -0.0001
Data Index: 530021 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9237. Min Range: -1.9237
Max Act: 1.3136. Min Act: -0.0001
Data Index: 1228805 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9237. Min Range: -1.9237
Max Act: 1.5069. Min Act: -0.0001
Data Index: 1180617 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9237. Min Range: -1.9237
Max Act: 1.1769. Min Act: -0.0001
Data Index: 154581 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9237. Min Range: -1.9237
Max Act: 1.1560. Min Act: -0.0001
Data Index: 1111606 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9237. Min Range: -1.9237
Max Act: 1.2119. Min Act: -0.0001
Data Index: 967643 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9237. Min Range: -1.9237
Max Act: 1.2817. Min Act: -0.0001
Data Index: 1197181 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9237. Min Range: -1.9237
Max Act: 1.1593. Min Act: -0.0001
Data Index: 1422156 (Python Code)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9237. Min Range: -1.9237
Max Act: 1.0761. Min Act: -0.0001
Data Index: 1123762 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9237. Min Range: -1.9237
Max Act: 1.0675. Min Act: -0.0001
Data Index: 544741 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9237. Min Range: -1.9237
Max Act: 1.1186. Min Act: -0.0001
Data Index: 379228 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9237. Min Range: -1.9237
Max Act: 1.0895. Min Act: -0.0001
Data Index: 1125906 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9237. Min Range: -1.9237
Max Act: 1.1776. Min Act: -0.0001
Data Index: 785216 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9237. Min Range: -1.9237
Max Act: 1.0650. Min Act: -0.0001
Data Index: 481540 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9237. Min Range: -1.9237
Max Act: 1.0976. Min Act: -0.0001
Data Index: 248976 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9237. Min Range: -1.9237
Max Act: 1.1142. Min Act: -0.0001
Data Index: 514691 (C4 (Web Text))
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9237. Min Range: -1.9237
Max Act: 1.0470. Min Act: -0.0001
Data Index: 1467133 (Python Code)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19