Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 60 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.8863. Min Range: -4.8863
Max Act: 4.8863. Min Act: -0.1700
Data Index: 106946 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8863. Min Range: -4.8863
Max Act: 4.8863. Min Act: -0.1700
Data Index: 133428 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8863. Min Range: -4.8863
Max Act: 4.8550. Min Act: -0.1700
Data Index: 1101858 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8863. Min Range: -4.8863
Max Act: 4.8550. Min Act: -0.1700
Data Index: 577559 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8863. Min Range: -4.8863
Max Act: 4.8238. Min Act: -0.1700
Data Index: 22722 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8863. Min Range: -4.8863
Max Act: 4.7925. Min Act: -0.1700
Data Index: 744246 (C4 (Web Text))
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8863. Min Range: -4.8863
Max Act: 4.8238. Min Act: -0.1700
Data Index: 18399 (C4 (Web Text))
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8863. Min Range: -4.8863
Max Act: 4.7300. Min Act: -0.1700
Data Index: 1092356 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8863. Min Range: -4.8863
Max Act: 4.7300. Min Act: -0.1700
Data Index: 1111596 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8863. Min Range: -4.8863
Max Act: 4.7300. Min Act: -0.1700
Data Index: 1327149 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8863. Min Range: -4.8863
Max Act: 4.6363. Min Act: -0.1700
Data Index: 920973 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8863. Min Range: -4.8863
Max Act: 4.6988. Min Act: -0.1700
Data Index: 481136 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8863. Min Range: -4.8863
Max Act: 4.6988. Min Act: -0.1700
Data Index: 579544 (C4 (Web Text))
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8863. Min Range: -4.8863
Max Act: 4.6988. Min Act: -0.1700
Data Index: 945157 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8863. Min Range: -4.8863
Max Act: 4.6675. Min Act: -0.1700
Data Index: 1283252 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8863. Min Range: -4.8863
Max Act: 4.6675. Min Act: -0.1700
Data Index: 1235058 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8863. Min Range: -4.8863
Max Act: 4.6675. Min Act: -0.1700
Data Index: 215899 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8863. Min Range: -4.8863
Max Act: 4.6363. Min Act: -0.1700
Data Index: 318982 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8863. Min Range: -4.8863
Max Act: 4.6675. Min Act: -0.1700
Data Index: 196157 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8863. Min Range: -4.8863
Max Act: 4.6363. Min Act: -0.1700
Data Index: 814570 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19