Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3171 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4818. Min Range: -8.4818
Max Act: 8.4818. Min Act: -0.1700
Data Index: 7931516 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4818. Min Range: -8.4818
Max Act: 8.4193. Min Act: -0.1700
Data Index: 7246393 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4818. Min Range: -8.4818
Max Act: 8.2943. Min Act: -0.1700
Data Index: 428361 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4818. Min Range: -8.4818
Max Act: 8.2318. Min Act: -0.1700
Data Index: 2902450 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4818. Min Range: -8.4818
Max Act: 8.1068. Min Act: -0.1700
Data Index: 7731398 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4818. Min Range: -8.4818
Max Act: 8.1068. Min Act: -0.1700
Data Index: 4799191 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4818. Min Range: -8.4818
Max Act: 8.0443. Min Act: -0.1700
Data Index: 121502 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4818. Min Range: -8.4818
Max Act: 8.0443. Min Act: -0.1700
Data Index: 523247 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4818. Min Range: -8.4818
Max Act: 8.0443. Min Act: -0.1700
Data Index: 3980043 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4818. Min Range: -8.4818
Max Act: 7.9818. Min Act: -0.1700
Data Index: 2035067 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4818. Min Range: -8.4818
Max Act: 7.9818. Min Act: -0.1700
Data Index: 3430757 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4818. Min Range: -8.4818
Max Act: 7.9193. Min Act: -0.1700
Data Index: 3226828 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4818. Min Range: -8.4818
Max Act: 7.9193. Min Act: -0.1700
Data Index: 755099 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4818. Min Range: -8.4818
Max Act: 7.9193. Min Act: -0.1700
Data Index: 5484143 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4818. Min Range: -8.4818
Max Act: 7.9193. Min Act: -0.1700
Data Index: 1912453 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4818. Min Range: -8.4818
Max Act: 7.8568. Min Act: -0.1700
Data Index: 1181314 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4818. Min Range: -8.4818
Max Act: 7.8568. Min Act: -0.1700
Data Index: 1956775 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4818. Min Range: -8.4818
Max Act: 7.8568. Min Act: -0.1700
Data Index: 7682813 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4818. Min Range: -8.4818
Max Act: 7.7943. Min Act: -0.1700
Data Index: 1685058 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4818. Min Range: -8.4818
Max Act: 7.8568. Min Act: -0.1700
Data Index: 6373050 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19