Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1643 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.6662. Min Range: -2.6662
Max Act: 2.6662. Min Act: -0.0001
Data Index: 15950 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6662. Min Range: -2.6662
Max Act: 2.1386. Min Act: -0.0001
Data Index: 30395 (C4 (Web Text))
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6662. Min Range: -2.6662
Max Act: 2.3123. Min Act: -0.0001
Data Index: 920495 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6662. Min Range: -2.6662
Max Act: 1.9216. Min Act: -0.0001
Data Index: 1105393 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6662. Min Range: -2.6662
Max Act: 2.2601. Min Act: -0.0001
Data Index: 29176 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6662. Min Range: -2.6662
Max Act: 1.7364. Min Act: -0.0001
Data Index: 132426 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6662. Min Range: -2.6662
Max Act: 1.9561. Min Act: -0.0001
Data Index: 734461 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6662. Min Range: -2.6662
Max Act: 2.0442. Min Act: -0.0001
Data Index: 814155 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6662. Min Range: -2.6662
Max Act: 1.9179. Min Act: -0.0001
Data Index: 287607 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6662. Min Range: -2.6662
Max Act: 1.8268. Min Act: -0.0001
Data Index: 1118799 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6662. Min Range: -2.6662
Max Act: 1.7487. Min Act: -0.0001
Data Index: 1201540 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6662. Min Range: -2.6662
Max Act: 1.8947. Min Act: -0.0001
Data Index: 657150 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6662. Min Range: -2.6662
Max Act: 1.9976. Min Act: -0.0001
Data Index: 1207334 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6662. Min Range: -2.6662
Max Act: 1.8874. Min Act: -0.0001
Data Index: 211984 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6662. Min Range: -2.6662
Max Act: 1.7730. Min Act: -0.0001
Data Index: 742815 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6662. Min Range: -2.6662
Max Act: 1.7078. Min Act: -0.0001
Data Index: 247072 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6662. Min Range: -2.6662
Max Act: 1.8501. Min Act: -0.0001
Data Index: 188828 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6662. Min Range: -2.6662
Max Act: 1.7522. Min Act: -0.0001
Data Index: 1104803 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6662. Min Range: -2.6662
Max Act: 1.7449. Min Act: -0.0001
Data Index: 504859 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6662. Min Range: -2.6662
Max Act: 1.6930. Min Act: -0.0001
Data Index: 1143778 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19