Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3825 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.2733. Min Range: -8.2733
Max Act: 8.2733. Min Act: -0.1700
Data Index: 5752048 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2733. Min Range: -8.2733
Max Act: 8.1795. Min Act: -0.1700
Data Index: 4835224 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2733. Min Range: -8.2733
Max Act: 8.1170. Min Act: -0.1700
Data Index: 6277070 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2733. Min Range: -8.2733
Max Act: 8.0545. Min Act: -0.1700
Data Index: 6228856 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2733. Min Range: -8.2733
Max Act: 7.9920. Min Act: -0.1700
Data Index: 5253461 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2733. Min Range: -8.2733
Max Act: 7.8983. Min Act: -0.1700
Data Index: 4268379 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2733. Min Range: -8.2733
Max Act: 7.8358. Min Act: -0.1700
Data Index: 4045112 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2733. Min Range: -8.2733
Max Act: 7.8358. Min Act: -0.1700
Data Index: 3255996 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2733. Min Range: -8.2733
Max Act: 7.8358. Min Act: -0.1700
Data Index: 2380837 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2733. Min Range: -8.2733
Max Act: 7.8358. Min Act: -0.1700
Data Index: 131729 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2733. Min Range: -8.2733
Max Act: 7.8358. Min Act: -0.1700
Data Index: 7284152 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2733. Min Range: -8.2733
Max Act: 7.8045. Min Act: -0.1700
Data Index: 6715866 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2733. Min Range: -8.2733
Max Act: 7.7420. Min Act: -0.1700
Data Index: 553650 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2733. Min Range: -8.2733
Max Act: 7.7108. Min Act: -0.1700
Data Index: 46582 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2733. Min Range: -8.2733
Max Act: 7.6795. Min Act: -0.1700
Data Index: 6413195 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2733. Min Range: -8.2733
Max Act: 7.6795. Min Act: -0.1700
Data Index: 6615864 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2733. Min Range: -8.2733
Max Act: 7.6483. Min Act: -0.1700
Data Index: 754319 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2733. Min Range: -8.2733
Max Act: 7.6483. Min Act: -0.1700
Data Index: 5752051 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2733. Min Range: -8.2733
Max Act: 7.5858. Min Act: -0.1700
Data Index: 1671460 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2733. Min Range: -8.2733
Max Act: 7.5858. Min Act: -0.1700
Data Index: 5752038 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19