Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 111 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.1849. Min Range: -4.1849
Max Act: 4.1849. Min Act: -0.1700
Data Index: 611508 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1849. Min Range: -4.1849
Max Act: 4.1849. Min Act: -0.1700
Data Index: 907025 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1849. Min Range: -4.1849
Max Act: 4.0912. Min Act: -0.1700
Data Index: 64931 (C4 (Web Text))
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1849. Min Range: -4.1849
Max Act: 4.1224. Min Act: -0.1700
Data Index: 621443 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1849. Min Range: -4.1849
Max Act: 4.0912. Min Act: -0.1700
Data Index: 499173 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1849. Min Range: -4.1849
Max Act: 4.0912. Min Act: -0.1700
Data Index: 563941 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1849. Min Range: -4.1849
Max Act: 4.0599. Min Act: -0.1700
Data Index: 159086 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1849. Min Range: -4.1849
Max Act: 3.9974. Min Act: -0.1700
Data Index: 935328 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1849. Min Range: -4.1849
Max Act: 4.0286. Min Act: -0.1700
Data Index: 1241035 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1849. Min Range: -4.1849
Max Act: 3.9974. Min Act: -0.1700
Data Index: 234830 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1849. Min Range: -4.1849
Max Act: 3.9661. Min Act: -0.1700
Data Index: 1097510 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1849. Min Range: -4.1849
Max Act: 3.9661. Min Act: -0.1700
Data Index: 190442 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1849. Min Range: -4.1849
Max Act: 3.9661. Min Act: -0.1700
Data Index: 1225951 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1849. Min Range: -4.1849
Max Act: 3.9348. Min Act: -0.1700
Data Index: 866249 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1849. Min Range: -4.1849
Max Act: 3.9036. Min Act: -0.1700
Data Index: 459006 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1849. Min Range: -4.1849
Max Act: 3.9348. Min Act: -0.1700
Data Index: 123309 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1849. Min Range: -4.1849
Max Act: 3.9348. Min Act: -0.1700
Data Index: 712659 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1849. Min Range: -4.1849
Max Act: 3.9036. Min Act: -0.1700
Data Index: 275358 (C4 (Web Text))
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1849. Min Range: -4.1849
Max Act: 3.8723. Min Act: -0.1700
Data Index: 762944 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1849. Min Range: -4.1849
Max Act: 3.8723. Min Act: -0.1700
Data Index: 523401 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19