Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5114 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0197. Min Range: -7.0197
Max Act: 7.0197. Min Act: -0.1700
Data Index: 5278189 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0197. Min Range: -7.0197
Max Act: 6.9885. Min Act: -0.1700
Data Index: 3014727 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0197. Min Range: -7.0197
Max Act: 6.9572. Min Act: -0.1700
Data Index: 6547627 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0197. Min Range: -7.0197
Max Act: 6.9260. Min Act: -0.1700
Data Index: 344086 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0197. Min Range: -7.0197
Max Act: 6.7697. Min Act: -0.1700
Data Index: 4813937 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0197. Min Range: -7.0197
Max Act: 6.7385. Min Act: -0.1700
Data Index: 1479519 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0197. Min Range: -7.0197
Max Act: 6.7072. Min Act: -0.1700
Data Index: 805203 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0197. Min Range: -7.0197
Max Act: 6.7072. Min Act: -0.1700
Data Index: 1848650 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0197. Min Range: -7.0197
Max Act: 6.7072. Min Act: -0.1700
Data Index: 1846728 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0197. Min Range: -7.0197
Max Act: 6.7072. Min Act: -0.1700
Data Index: 7121418 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0197. Min Range: -7.0197
Max Act: 6.6447. Min Act: -0.1700
Data Index: 5844025 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0197. Min Range: -7.0197
Max Act: 6.6447. Min Act: -0.1700
Data Index: 1285122 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0197. Min Range: -7.0197
Max Act: 6.6447. Min Act: -0.1700
Data Index: 644254 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0197. Min Range: -7.0197
Max Act: 6.6447. Min Act: -0.1700
Data Index: 1111154 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0197. Min Range: -7.0197
Max Act: 6.6135. Min Act: -0.1700
Data Index: 3239889 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0197. Min Range: -7.0197
Max Act: 6.6447. Min Act: -0.1700
Data Index: 6649806 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0197. Min Range: -7.0197
Max Act: 6.6135. Min Act: -0.1700
Data Index: 804929 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0197. Min Range: -7.0197
Max Act: 6.6135. Min Act: -0.1700
Data Index: 2521935 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0197. Min Range: -7.0197
Max Act: 6.6135. Min Act: -0.1700
Data Index: 4880517 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0197. Min Range: -7.0197
Max Act: 6.5822. Min Act: -0.1700
Data Index: 3401566 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #19