Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1963 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.9261. Min Range: -2.9261
Max Act: 2.9261. Min Act: -0.0001
Data Index: 424563 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9261. Min Range: -2.9261
Max Act: 2.3492. Min Act: -0.0001
Data Index: 894000 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9261. Min Range: -2.9261
Max Act: 1.9771. Min Act: -0.0001
Data Index: 1296800 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9261. Min Range: -2.9261
Max Act: 1.9575. Min Act: -0.0001
Data Index: 821667 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9261. Min Range: -2.9261
Max Act: 1.9371. Min Act: -0.0001
Data Index: 1462745 (Python Code)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9261. Min Range: -2.9261
Max Act: 1.9092. Min Act: -0.0001
Data Index: 1262502 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9261. Min Range: -2.9261
Max Act: 1.6628. Min Act: -0.0001
Data Index: 63880 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9261. Min Range: -2.9261
Max Act: 1.4088. Min Act: -0.0001
Data Index: 64494 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9261. Min Range: -2.9261
Max Act: 1.4391. Min Act: -0.0001
Data Index: 64107 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9261. Min Range: -2.9261
Max Act: 1.2346. Min Act: -0.0001
Data Index: 1199320 (C4 (Web Text))
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9261. Min Range: -2.9261
Max Act: 1.0984. Min Act: -0.0001
Data Index: 1393631 (Python Code)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9261. Min Range: -2.9261
Max Act: 1.1617. Min Act: -0.0001
Data Index: 274348 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9261. Min Range: -2.9261
Max Act: 1.0998. Min Act: -0.0001
Data Index: 1073659 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9261. Min Range: -2.9261
Max Act: 1.1655. Min Act: -0.0001
Data Index: 875033 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9261. Min Range: -2.9261
Max Act: 1.0862. Min Act: -0.0001
Data Index: 1638374 (Python Code)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9261. Min Range: -2.9261
Max Act: 1.0594. Min Act: -0.0001
Data Index: 1487621 (Python Code)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9261. Min Range: -2.9261
Max Act: 1.0653. Min Act: -0.0001
Data Index: 1065319 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9261. Min Range: -2.9261
Max Act: 1.0970. Min Act: -0.0001
Data Index: 1632751 (Python Code)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9261. Min Range: -2.9261
Max Act: 1.0249. Min Act: -0.0001
Data Index: 614644 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9261. Min Range: -2.9261
Max Act: 0.9652. Min Act: -0.0001
Data Index: 693076 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19