Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2661 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.5244. Min Range: -2.5244
Max Act: 2.5244. Min Act: -0.0001
Data Index: 243209 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5244. Min Range: -2.5244
Max Act: 2.5213. Min Act: -0.0001
Data Index: 665448 (C4 (Web Text))
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5244. Min Range: -2.5244
Max Act: 2.0902. Min Act: -0.0001
Data Index: 73762 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5244. Min Range: -2.5244
Max Act: 1.9410. Min Act: -0.0001
Data Index: 922718 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5244. Min Range: -2.5244
Max Act: 1.7862. Min Act: -0.0001
Data Index: 1181770 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5244. Min Range: -2.5244
Max Act: 1.7741. Min Act: -0.0001
Data Index: 305889 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5244. Min Range: -2.5244
Max Act: 1.7661. Min Act: -0.0001
Data Index: 302164 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5244. Min Range: -2.5244
Max Act: 1.8297. Min Act: -0.0001
Data Index: 816594 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5244. Min Range: -2.5244
Max Act: 1.6322. Min Act: -0.0001
Data Index: 448422 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5244. Min Range: -2.5244
Max Act: 1.6465. Min Act: -0.0001
Data Index: 108327 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5244. Min Range: -2.5244
Max Act: 1.5890. Min Act: -0.0001
Data Index: 774149 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5244. Min Range: -2.5244
Max Act: 1.5053. Min Act: -0.0001
Data Index: 1115353 (C4 (Web Text))
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5244. Min Range: -2.5244
Max Act: 1.6962. Min Act: -0.0001
Data Index: 1180642 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5244. Min Range: -2.5244
Max Act: 1.5869. Min Act: -0.0001
Data Index: 1218066 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5244. Min Range: -2.5244
Max Act: 1.5817. Min Act: -0.0001
Data Index: 430459 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5244. Min Range: -2.5244
Max Act: 1.4888. Min Act: -0.0001
Data Index: 1087965 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5244. Min Range: -2.5244
Max Act: 1.5416. Min Act: -0.0001
Data Index: 141062 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5244. Min Range: -2.5244
Max Act: 1.4405. Min Act: -0.0001
Data Index: 36740 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5244. Min Range: -2.5244
Max Act: 1.4901. Min Act: -0.0001
Data Index: 783918 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5244. Min Range: -2.5244
Max Act: 1.4045. Min Act: -0.0001
Data Index: 586244 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #19