Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 976 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3328. Min Range: -6.3328
Max Act: 6.3328. Min Act: -0.1700
Data Index: 6418930 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3328. Min Range: -6.3328
Max Act: 6.1766. Min Act: -0.1700
Data Index: 5069984 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3328. Min Range: -6.3328
Max Act: 6.2078. Min Act: -0.1700
Data Index: 1883559 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3328. Min Range: -6.3328
Max Act: 6.1453. Min Act: -0.1700
Data Index: 2680486 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3328. Min Range: -6.3328
Max Act: 6.1141. Min Act: -0.1700
Data Index: 5957298 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3328. Min Range: -6.3328
Max Act: 6.0828. Min Act: -0.1700
Data Index: 3823982 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3328. Min Range: -6.3328
Max Act: 6.0828. Min Act: -0.1700
Data Index: 1883166 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3328. Min Range: -6.3328
Max Act: 6.0828. Min Act: -0.1700
Data Index: 8387723 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3328. Min Range: -6.3328
Max Act: 6.0203. Min Act: -0.1700
Data Index: 5156183 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3328. Min Range: -6.3328
Max Act: 5.8953. Min Act: -0.1700
Data Index: 2213686 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3328. Min Range: -6.3328
Max Act: 5.9266. Min Act: -0.1700
Data Index: 6896939 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3328. Min Range: -6.3328
Max Act: 5.9266. Min Act: -0.1700
Data Index: 56237 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3328. Min Range: -6.3328
Max Act: 5.9266. Min Act: -0.1700
Data Index: 6941039 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3328. Min Range: -6.3328
Max Act: 5.8953. Min Act: -0.1700
Data Index: 1982216 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3328. Min Range: -6.3328
Max Act: 5.8953. Min Act: -0.1700
Data Index: 324094 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3328. Min Range: -6.3328
Max Act: 5.8953. Min Act: -0.1700
Data Index: 3913215 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3328. Min Range: -6.3328
Max Act: 5.8953. Min Act: -0.1700
Data Index: 2116797 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3328. Min Range: -6.3328
Max Act: 5.8641. Min Act: -0.1700
Data Index: 2725297 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3328. Min Range: -6.3328
Max Act: 5.8641. Min Act: -0.1700
Data Index: 1438404 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3328. Min Range: -6.3328
Max Act: 5.8328. Min Act: -0.1700
Data Index: 771049 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19