Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1008 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 3.4476. Min Range: -3.4476
Max Act: 3.4476. Min Act: -0.0001
Data Index: 65176 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4476. Min Range: -3.4476
Max Act: 3.2084. Min Act: -0.0001
Data Index: 1147169 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4476. Min Range: -3.4476
Max Act: 3.0120. Min Act: -0.0001
Data Index: 220344 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4476. Min Range: -3.4476
Max Act: 2.9365. Min Act: -0.0001
Data Index: 880038 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4476. Min Range: -3.4476
Max Act: 2.6037. Min Act: -0.0001
Data Index: 1178986 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4476. Min Range: -3.4476
Max Act: 2.6938. Min Act: -0.0001
Data Index: 294304 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4476. Min Range: -3.4476
Max Act: 2.7179. Min Act: -0.0001
Data Index: 1044708 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4476. Min Range: -3.4476
Max Act: 2.3091. Min Act: -0.0001
Data Index: 286996 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4476. Min Range: -3.4476
Max Act: 2.4272. Min Act: -0.0001
Data Index: 20505 (C4 (Web Text))
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4476. Min Range: -3.4476
Max Act: 2.1868. Min Act: -0.0001
Data Index: 474835 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4476. Min Range: -3.4476
Max Act: 2.4369. Min Act: -0.0001
Data Index: 1295519 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4476. Min Range: -3.4476
Max Act: 2.4549. Min Act: -0.0001
Data Index: 1128115 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4476. Min Range: -3.4476
Max Act: 2.3384. Min Act: -0.0001
Data Index: 1316820 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4476. Min Range: -3.4476
Max Act: 2.2896. Min Act: -0.0001
Data Index: 44354 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4476. Min Range: -3.4476
Max Act: 2.4051. Min Act: -0.0001
Data Index: 108801 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4476. Min Range: -3.4476
Max Act: 2.2729. Min Act: -0.0001
Data Index: 562406 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4476. Min Range: -3.4476
Max Act: 2.1603. Min Act: -0.0001
Data Index: 514424 (C4 (Web Text))
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4476. Min Range: -3.4476
Max Act: 2.2813. Min Act: -0.0001
Data Index: 414811 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4476. Min Range: -3.4476
Max Act: 2.1534. Min Act: -0.0001
Data Index: 643682 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4476. Min Range: -3.4476
Max Act: 2.2135. Min Act: -0.0001
Data Index: 302366 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #19