Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1203 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6092. Min Range: -6.6092
Max Act: 6.6092. Min Act: -0.1700
Data Index: 4227028 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6092. Min Range: -6.6092
Max Act: 6.5780. Min Act: -0.1700
Data Index: 2463315 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6092. Min Range: -6.6092
Max Act: 6.3905. Min Act: -0.1700
Data Index: 1901932 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6092. Min Range: -6.6092
Max Act: 6.3592. Min Act: -0.1700
Data Index: 1507228 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6092. Min Range: -6.6092
Max Act: 6.3280. Min Act: -0.1700
Data Index: 1210142 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6092. Min Range: -6.6092
Max Act: 6.2342. Min Act: -0.1700
Data Index: 3034878 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6092. Min Range: -6.6092
Max Act: 6.2342. Min Act: -0.1700
Data Index: 4229334 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6092. Min Range: -6.6092
Max Act: 6.2342. Min Act: -0.1700
Data Index: 2737474 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6092. Min Range: -6.6092
Max Act: 6.2030. Min Act: -0.1700
Data Index: 2329769 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6092. Min Range: -6.6092
Max Act: 6.1405. Min Act: -0.1700
Data Index: 4296294 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6092. Min Range: -6.6092
Max Act: 6.1405. Min Act: -0.1700
Data Index: 2005597 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6092. Min Range: -6.6092
Max Act: 6.1405. Min Act: -0.1700
Data Index: 5871121 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6092. Min Range: -6.6092
Max Act: 6.1405. Min Act: -0.1700
Data Index: 4382483 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6092. Min Range: -6.6092
Max Act: 6.1092. Min Act: -0.1700
Data Index: 8414429 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6092. Min Range: -6.6092
Max Act: 6.1092. Min Act: -0.1700
Data Index: 3703952 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6092. Min Range: -6.6092
Max Act: 6.1092. Min Act: -0.1700
Data Index: 5388882 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6092. Min Range: -6.6092
Max Act: 6.0780. Min Act: -0.1700
Data Index: 1348678 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6092. Min Range: -6.6092
Max Act: 6.0780. Min Act: -0.1700
Data Index: 8727813 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6092. Min Range: -6.6092
Max Act: 6.0467. Min Act: -0.1700
Data Index: 986810 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6092. Min Range: -6.6092
Max Act: 6.0467. Min Act: -0.1700
Data Index: 1009087 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19