Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2839 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.2669. Min Range: -2.2669
Max Act: 2.2669. Min Act: -0.0001
Data Index: 1046190 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2669. Min Range: -2.2669
Max Act: 2.2447. Min Act: -0.0001
Data Index: 141148 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2669. Min Range: -2.2669
Max Act: 1.9976. Min Act: -0.0001
Data Index: 1082016 (C4 (Web Text))
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2669. Min Range: -2.2669
Max Act: 1.8941. Min Act: -0.0001
Data Index: 404004 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2669. Min Range: -2.2669
Max Act: 1.8855. Min Act: -0.0001
Data Index: 1272086 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2669. Min Range: -2.2669
Max Act: 1.8786. Min Act: -0.0001
Data Index: 164085 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2669. Min Range: -2.2669
Max Act: 1.9083. Min Act: -0.0001
Data Index: 246665 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2669. Min Range: -2.2669
Max Act: 1.9066. Min Act: -0.0001
Data Index: 971570 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2669. Min Range: -2.2669
Max Act: 1.8381. Min Act: -0.0001
Data Index: 969823 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2669. Min Range: -2.2669
Max Act: 1.7778. Min Act: -0.0001
Data Index: 1086163 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2669. Min Range: -2.2669
Max Act: 1.8878. Min Act: -0.0001
Data Index: 524290 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2669. Min Range: -2.2669
Max Act: 1.8784. Min Act: -0.0001
Data Index: 469706 (C4 (Web Text))
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2669. Min Range: -2.2669
Max Act: 1.7651. Min Act: -0.0001
Data Index: 372139 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2669. Min Range: -2.2669
Max Act: 1.8159. Min Act: -0.0001
Data Index: 1268884 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2669. Min Range: -2.2669
Max Act: 1.8168. Min Act: -0.0001
Data Index: 946457 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2669. Min Range: -2.2669
Max Act: 1.7989. Min Act: -0.0001
Data Index: 866696 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2669. Min Range: -2.2669
Max Act: 1.8435. Min Act: -0.0001
Data Index: 761699 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2669. Min Range: -2.2669
Max Act: 1.8433. Min Act: -0.0001
Data Index: 1351224 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2669. Min Range: -2.2669
Max Act: 1.7361. Min Act: -0.0001
Data Index: 366142 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2669. Min Range: -2.2669
Max Act: 1.7748. Min Act: -0.0001
Data Index: 758951 (C4 (Web Text))
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19