Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 336 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6167. Min Range: -6.6167
Max Act: 6.6167. Min Act: -0.1700
Data Index: 8086695 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6167. Min Range: -6.6167
Max Act: 6.4292. Min Act: -0.1700
Data Index: 8375920 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6167. Min Range: -6.6167
Max Act: 6.2104. Min Act: -0.1700
Data Index: 7876903 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6167. Min Range: -6.6167
Max Act: 6.0854. Min Act: -0.1700
Data Index: 8332586 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6167. Min Range: -6.6167
Max Act: 6.0854. Min Act: -0.1700
Data Index: 396879 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6167. Min Range: -6.6167
Max Act: 6.0542. Min Act: -0.1700
Data Index: 2662398 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6167. Min Range: -6.6167
Max Act: 6.0542. Min Act: -0.1700
Data Index: 6640167 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6167. Min Range: -6.6167
Max Act: 6.0542. Min Act: -0.1700
Data Index: 5730324 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6167. Min Range: -6.6167
Max Act: 6.0229. Min Act: -0.1700
Data Index: 4921985 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6167. Min Range: -6.6167
Max Act: 6.0229. Min Act: -0.1700
Data Index: 7643826 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6167. Min Range: -6.6167
Max Act: 6.0229. Min Act: -0.1700
Data Index: 8273049 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6167. Min Range: -6.6167
Max Act: 5.9917. Min Act: -0.1700
Data Index: 1937939 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6167. Min Range: -6.6167
Max Act: 5.9604. Min Act: -0.1700
Data Index: 4263166 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6167. Min Range: -6.6167
Max Act: 5.9292. Min Act: -0.1700
Data Index: 4151270 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6167. Min Range: -6.6167
Max Act: 5.9292. Min Act: -0.1700
Data Index: 7395060 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6167. Min Range: -6.6167
Max Act: 5.9292. Min Act: -0.1700
Data Index: 1272240 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6167. Min Range: -6.6167
Max Act: 5.9292. Min Act: -0.1700
Data Index: 4222627 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6167. Min Range: -6.6167
Max Act: 5.9292. Min Act: -0.1700
Data Index: 5039098 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6167. Min Range: -6.6167
Max Act: 5.8979. Min Act: -0.1700
Data Index: 1263201 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6167. Min Range: -6.6167
Max Act: 5.8979. Min Act: -0.1700
Data Index: 2050897 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19