Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2246 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9416. Min Range: -6.9416
Max Act: 6.9416. Min Act: -0.1700
Data Index: 2483201 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9416. Min Range: -6.9416
Max Act: 6.8478. Min Act: -0.1700
Data Index: 6903503 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9416. Min Range: -6.9416
Max Act: 6.7228. Min Act: -0.1700
Data Index: 7672751 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9416. Min Range: -6.9416
Max Act: 6.7228. Min Act: -0.1700
Data Index: 1012342 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9416. Min Range: -6.9416
Max Act: 6.6916. Min Act: -0.1700
Data Index: 4555947 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9416. Min Range: -6.9416
Max Act: 6.6916. Min Act: -0.1700
Data Index: 108111 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9416. Min Range: -6.9416
Max Act: 6.6603. Min Act: -0.1700
Data Index: 6565775 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9416. Min Range: -6.9416
Max Act: 6.6291. Min Act: -0.1700
Data Index: 5101257 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9416. Min Range: -6.9416
Max Act: 6.5666. Min Act: -0.1700
Data Index: 2723051 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9416. Min Range: -6.9416
Max Act: 6.5353. Min Act: -0.1700
Data Index: 6129930 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9416. Min Range: -6.9416
Max Act: 6.4728. Min Act: -0.1700
Data Index: 1819889 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9416. Min Range: -6.9416
Max Act: 6.4728. Min Act: -0.1700
Data Index: 2292817 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9416. Min Range: -6.9416
Max Act: 6.4416. Min Act: -0.1700
Data Index: 1060923 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9416. Min Range: -6.9416
Max Act: 6.4416. Min Act: -0.1700
Data Index: 1410278 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9416. Min Range: -6.9416
Max Act: 6.4103. Min Act: -0.1700
Data Index: 5963066 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9416. Min Range: -6.9416
Max Act: 6.4416. Min Act: -0.1700
Data Index: 5359264 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9416. Min Range: -6.9416
Max Act: 6.4416. Min Act: -0.1700
Data Index: 758289 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9416. Min Range: -6.9416
Max Act: 6.4103. Min Act: -0.1700
Data Index: 8744610 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9416. Min Range: -6.9416
Max Act: 6.4103. Min Act: -0.1700
Data Index: 5018520 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9416. Min Range: -6.9416
Max Act: 6.4103. Min Act: -0.1700
Data Index: 5601759 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19