Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2242 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.8865. Min Range: -0.8865
Max Act: 0.8848. Min Act: -0.0001
Data Index: 1432245 (Python Code)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8865. Min Range: -0.8865
Max Act: 0.8865. Min Act: -0.0001
Data Index: 1550533 (Python Code)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8865. Min Range: -0.8865
Max Act: 0.8646. Min Act: -0.0001
Data Index: 1582372 (Python Code)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8865. Min Range: -0.8865
Max Act: 0.8265. Min Act: -0.0001
Data Index: 1523040 (Python Code)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8865. Min Range: -0.8865
Max Act: 0.7904. Min Act: -0.0001
Data Index: 1431706 (Python Code)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8865. Min Range: -0.8865
Max Act: 0.7824. Min Act: -0.0001
Data Index: 1592719 (Python Code)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8865. Min Range: -0.8865
Max Act: 0.7818. Min Act: -0.0001
Data Index: 1613360 (Python Code)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8865. Min Range: -0.8865
Max Act: 0.7678. Min Act: -0.0001
Data Index: 1443366 (Python Code)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8865. Min Range: -0.8865
Max Act: 0.5364. Min Act: -0.0001
Data Index: 1481921 (Python Code)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8865. Min Range: -0.8865
Max Act: 0.5488. Min Act: -0.0001
Data Index: 1195483 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8865. Min Range: -0.8865
Max Act: 0.5653. Min Act: -0.0001
Data Index: 1362889 (Python Code)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8865. Min Range: -0.8865
Max Act: 0.5289. Min Act: -0.0001
Data Index: 1509651 (Python Code)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8865. Min Range: -0.8865
Max Act: 0.5171. Min Act: -0.0001
Data Index: 662656 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8865. Min Range: -0.8865
Max Act: 0.4687. Min Act: -0.0001
Data Index: 1070589 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8865. Min Range: -0.8865
Max Act: 0.4918. Min Act: -0.0001
Data Index: 309468 (C4 (Web Text))
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8865. Min Range: -0.8865
Max Act: 0.4781. Min Act: -0.0001
Data Index: 1448778 (Python Code)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8865. Min Range: -0.8865
Max Act: 0.4444. Min Act: -0.0001
Data Index: 1404465 (Python Code)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8865. Min Range: -0.8865
Max Act: 0.4768. Min Act: -0.0001
Data Index: 1074870 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8865. Min Range: -0.8865
Max Act: 0.4401. Min Act: -0.0001
Data Index: 1570489 (Python Code)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8865. Min Range: -0.8865
Max Act: 0.4592. Min Act: -0.0001
Data Index: 1632066 (Python Code)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19