Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 722 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3671. Min Range: -5.3671
Max Act: 5.3671. Min Act: -0.1700
Data Index: 3345776 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3671. Min Range: -5.3671
Max Act: 5.2734. Min Act: -0.1700
Data Index: 4490839 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3671. Min Range: -5.3671
Max Act: 5.2109. Min Act: -0.1700
Data Index: 8554694 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3671. Min Range: -5.3671
Max Act: 5.1796. Min Act: -0.1700
Data Index: 2682748 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3671. Min Range: -5.3671
Max Act: 5.1484. Min Act: -0.1700
Data Index: 8329406 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3671. Min Range: -5.3671
Max Act: 5.1796. Min Act: -0.1700
Data Index: 4604581 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3671. Min Range: -5.3671
Max Act: 5.1796. Min Act: -0.1700
Data Index: 7493821 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3671. Min Range: -5.3671
Max Act: 5.1484. Min Act: -0.1700
Data Index: 5647954 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3671. Min Range: -5.3671
Max Act: 5.1484. Min Act: -0.1700
Data Index: 7641752 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3671. Min Range: -5.3671
Max Act: 5.1171. Min Act: -0.1700
Data Index: 4246355 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3671. Min Range: -5.3671
Max Act: 5.0859. Min Act: -0.1700
Data Index: 8791411 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3671. Min Range: -5.3671
Max Act: 5.0859. Min Act: -0.1700
Data Index: 4148391 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3671. Min Range: -5.3671
Max Act: 5.0859. Min Act: -0.1700
Data Index: 4247466 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3671. Min Range: -5.3671
Max Act: 5.0859. Min Act: -0.1700
Data Index: 7907795 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3671. Min Range: -5.3671
Max Act: 5.0234. Min Act: -0.1700
Data Index: 6398929 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3671. Min Range: -5.3671
Max Act: 5.0234. Min Act: -0.1700
Data Index: 4719324 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3671. Min Range: -5.3671
Max Act: 5.0234. Min Act: -0.1700
Data Index: 6698809 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3671. Min Range: -5.3671
Max Act: 5.0234. Min Act: -0.1700
Data Index: 1203328 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3671. Min Range: -5.3671
Max Act: 5.0234. Min Act: -0.1700
Data Index: 2316862 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3671. Min Range: -5.3671
Max Act: 5.0234. Min Act: -0.1700
Data Index: 4930784 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19