Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 17 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.8814. Min Range: -1.8814
Max Act: 1.7897. Min Act: -0.0001
Data Index: 1092587 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8814. Min Range: -1.8814
Max Act: 1.8814. Min Act: -0.0001
Data Index: 683276 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8814. Min Range: -1.8814
Max Act: 1.7384. Min Act: -0.0001
Data Index: 319430 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8814. Min Range: -1.8814
Max Act: 1.6552. Min Act: -0.0001
Data Index: 1018406 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8814. Min Range: -1.8814
Max Act: 1.6524. Min Act: -0.0001
Data Index: 924401 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8814. Min Range: -1.8814
Max Act: 1.6266. Min Act: -0.0001
Data Index: 819233 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8814. Min Range: -1.8814
Max Act: 1.5805. Min Act: -0.0001
Data Index: 241857 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8814. Min Range: -1.8814
Max Act: 1.6219. Min Act: -0.0001
Data Index: 1005465 (C4 (Web Text))
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8814. Min Range: -1.8814
Max Act: 1.6487. Min Act: -0.0001
Data Index: 1002951 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8814. Min Range: -1.8814
Max Act: 1.6039. Min Act: -0.0001
Data Index: 1199362 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8814. Min Range: -1.8814
Max Act: 1.5530. Min Act: -0.0001
Data Index: 1005409 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8814. Min Range: -1.8814
Max Act: 1.5452. Min Act: -0.0001
Data Index: 1302203 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8814. Min Range: -1.8814
Max Act: 1.5803. Min Act: -0.0001
Data Index: 876096 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8814. Min Range: -1.8814
Max Act: 1.5068. Min Act: -0.0001
Data Index: 930898 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8814. Min Range: -1.8814
Max Act: 1.5138. Min Act: -0.0001
Data Index: 1277324 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8814. Min Range: -1.8814
Max Act: 1.5055. Min Act: -0.0001
Data Index: 1359088 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8814. Min Range: -1.8814
Max Act: 1.5833. Min Act: -0.0001
Data Index: 1304890 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8814. Min Range: -1.8814
Max Act: 1.4743. Min Act: -0.0001
Data Index: 541483 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8814. Min Range: -1.8814
Max Act: 1.4973. Min Act: -0.0001
Data Index: 1126846 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8814. Min Range: -1.8814
Max Act: 1.5355. Min Act: -0.0001
Data Index: 296826 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #19