Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3194 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.1652. Min Act: -0.1700
Data Index: 2626402 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.1339. Min Act: -0.1700
Data Index: 1775259 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.1027. Min Act: -0.1700
Data Index: 6110791 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.1027. Min Act: -0.1700
Data Index: 7393281 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.1652. Min Act: -0.1700
Data Index: 7348406 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.1339. Min Act: -0.1700
Data Index: 2970942 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.0714. Min Act: -0.1700
Data Index: 608983 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.1027. Min Act: -0.1700
Data Index: 2348072 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.0402. Min Act: -0.1700
Data Index: 316320 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.0402. Min Act: -0.1700
Data Index: 2215682 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.0402. Min Act: -0.1700
Data Index: 4892027 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.0089. Min Act: -0.1700
Data Index: 5476078 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.0089. Min Act: -0.1700
Data Index: 4186639 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.0089. Min Act: -0.1700
Data Index: 7128937 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.0089. Min Act: -0.1700
Data Index: 3584387 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.0402. Min Act: -0.1700
Data Index: 2035607 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.0089. Min Act: -0.1700
Data Index: 1569556 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1652. Min Range: -5.1652
Max Act: 4.9777. Min Act: -0.1700
Data Index: 3983359 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1652. Min Range: -5.1652
Max Act: 4.9777. Min Act: -0.1700
Data Index: 5127487 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.0089. Min Act: -0.1700
Data Index: 4335980 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19