Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1780 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.0278. Min Range: -0.0278
Max Act: 0.0278. Min Act: -0.0001
Data Index: 1453618 (Python Code)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0278. Min Range: -0.0278
Max Act: 0.0211. Min Act: -0.0001
Data Index: 1448283 (Python Code)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0278. Min Range: -0.0278
Max Act: 0.0163. Min Act: -0.0001
Data Index: 764703 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0278. Min Range: -0.0278
Max Act: 0.0170. Min Act: -0.0001
Data Index: 1388698 (Python Code)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0278. Min Range: -0.0278
Max Act: 0.0184. Min Act: -0.0001
Data Index: 1393852 (Python Code)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0278. Min Range: -0.0278
Max Act: 0.0163. Min Act: -0.0001
Data Index: 1397443 (Python Code)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0278. Min Range: -0.0278
Max Act: 0.0172. Min Act: -0.0001
Data Index: 639186 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0278. Min Range: -0.0278
Max Act: 0.0201. Min Act: -0.0001
Data Index: 1307283 (C4 (Web Text))
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0278. Min Range: -0.0278
Max Act: 0.0170. Min Act: -0.0001
Data Index: 1468283 (Python Code)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0278. Min Range: -0.0278
Max Act: 0.0162. Min Act: -0.0001
Data Index: 1546452 (Python Code)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0278. Min Range: -0.0278
Max Act: 0.0145. Min Act: -0.0001
Data Index: 1539366 (Python Code)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0278. Min Range: -0.0278
Max Act: 0.0161. Min Act: -0.0001
Data Index: 1378170 (Python Code)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0278. Min Range: -0.0278
Max Act: 0.0169. Min Act: -0.0001
Data Index: 1147685 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0278. Min Range: -0.0278
Max Act: 0.0152. Min Act: -0.0001
Data Index: 357509 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0278. Min Range: -0.0278
Max Act: 0.0151. Min Act: -0.0001
Data Index: 140651 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0278. Min Range: -0.0278
Max Act: 0.0140. Min Act: -0.0001
Data Index: 1627648 (Python Code)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0278. Min Range: -0.0278
Max Act: 0.0154. Min Act: -0.0001
Data Index: 1331856 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0278. Min Range: -0.0278
Max Act: 0.0151. Min Act: -0.0001
Data Index: 1604904 (Python Code)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0278. Min Range: -0.0278
Max Act: 0.0138. Min Act: -0.0001
Data Index: 1582088 (Python Code)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0278. Min Range: -0.0278
Max Act: 0.0146. Min Act: -0.0001
Data Index: 1489950 (Python Code)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19