Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3976 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.2279. Min Range: -9.2279
Max Act: 9.2279. Min Act: -0.1700
Data Index: 2291329 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2279. Min Range: -9.2279
Max Act: 9.1654. Min Act: -0.1700
Data Index: 5551650 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2279. Min Range: -9.2279
Max Act: 9.1654. Min Act: -0.1700
Data Index: 3190340 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2279. Min Range: -9.2279
Max Act: 8.9779. Min Act: -0.1700
Data Index: 7488241 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2279. Min Range: -9.2279
Max Act: 9.0404. Min Act: -0.1700
Data Index: 5857108 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2279. Min Range: -9.2279
Max Act: 8.9779. Min Act: -0.1700
Data Index: 8473862 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2279. Min Range: -9.2279
Max Act: 8.9779. Min Act: -0.1700
Data Index: 3455161 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2279. Min Range: -9.2279
Max Act: 8.9779. Min Act: -0.1700
Data Index: 4951980 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2279. Min Range: -9.2279
Max Act: 8.9779. Min Act: -0.1700
Data Index: 8096398 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2279. Min Range: -9.2279
Max Act: 8.9779. Min Act: -0.1700
Data Index: 342508 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2279. Min Range: -9.2279
Max Act: 8.8529. Min Act: -0.1700
Data Index: 808124 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2279. Min Range: -9.2279
Max Act: 8.9779. Min Act: -0.1700
Data Index: 1719859 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2279. Min Range: -9.2279
Max Act: 8.8529. Min Act: -0.1700
Data Index: 1306008 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2279. Min Range: -9.2279
Max Act: 8.8529. Min Act: -0.1700
Data Index: 763601 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2279. Min Range: -9.2279
Max Act: 8.8529. Min Act: -0.1700
Data Index: 811612 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2279. Min Range: -9.2279
Max Act: 8.7904. Min Act: -0.1700
Data Index: 3271904 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2279. Min Range: -9.2279
Max Act: 8.7904. Min Act: -0.1700
Data Index: 5953323 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2279. Min Range: -9.2279
Max Act: 8.7904. Min Act: -0.1700
Data Index: 7309768 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2279. Min Range: -9.2279
Max Act: 8.7904. Min Act: -0.1700
Data Index: 5241783 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2279. Min Range: -9.2279
Max Act: 8.7904. Min Act: -0.1700
Data Index: 8118143 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19