Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2020 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.9434. Min Range: -4.9434
Max Act: 4.9434. Min Act: -0.1700
Data Index: 172874 (C4 (Web Text))
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9434. Min Range: -4.9434
Max Act: 4.7872. Min Act: -0.1700
Data Index: 1322282 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9434. Min Range: -4.9434
Max Act: 4.7247. Min Act: -0.1700
Data Index: 879404 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9434. Min Range: -4.9434
Max Act: 4.7559. Min Act: -0.1700
Data Index: 1140299 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9434. Min Range: -4.9434
Max Act: 4.7872. Min Act: -0.1700
Data Index: 930197 (C4 (Web Text))
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9434. Min Range: -4.9434
Max Act: 4.7247. Min Act: -0.1700
Data Index: 50847 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9434. Min Range: -4.9434
Max Act: 4.6934. Min Act: -0.1700
Data Index: 801330 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9434. Min Range: -4.9434
Max Act: 4.6934. Min Act: -0.1700
Data Index: 1337875 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9434. Min Range: -4.9434
Max Act: 4.6309. Min Act: -0.1700
Data Index: 1072525 (C4 (Web Text))
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9434. Min Range: -4.9434
Max Act: 4.6934. Min Act: -0.1700
Data Index: 995870 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9434. Min Range: -4.9434
Max Act: 4.6934. Min Act: -0.1700
Data Index: 4106 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9434. Min Range: -4.9434
Max Act: 4.6934. Min Act: -0.1700
Data Index: 1023607 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9434. Min Range: -4.9434
Max Act: 4.6622. Min Act: -0.1700
Data Index: 210532 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9434. Min Range: -4.9434
Max Act: 4.6934. Min Act: -0.1700
Data Index: 522117 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9434. Min Range: -4.9434
Max Act: 4.7247. Min Act: -0.1700
Data Index: 580574 (C4 (Web Text))
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9434. Min Range: -4.9434
Max Act: 4.6934. Min Act: -0.1700
Data Index: 619705 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9434. Min Range: -4.9434
Max Act: 4.6622. Min Act: -0.1700
Data Index: 1109234 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9434. Min Range: -4.9434
Max Act: 4.6934. Min Act: -0.1700
Data Index: 696377 (C4 (Web Text))
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9434. Min Range: -4.9434
Max Act: 4.6622. Min Act: -0.1700
Data Index: 1520096 (Python Code)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9434. Min Range: -4.9434
Max Act: 4.7247. Min Act: -0.1700
Data Index: 1553319 (Python Code)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19