Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2799 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8100. Min Range: -8.8100
Max Act: 8.8100. Min Act: -0.1700
Data Index: 1587127 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8100. Min Range: -8.8100
Max Act: 8.5600. Min Act: -0.1700
Data Index: 8560718 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8100. Min Range: -8.8100
Max Act: 8.4975. Min Act: -0.1700
Data Index: 1942064 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8100. Min Range: -8.8100
Max Act: 8.4350. Min Act: -0.1700
Data Index: 2880779 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8100. Min Range: -8.8100
Max Act: 8.3725. Min Act: -0.1700
Data Index: 3587296 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8100. Min Range: -8.8100
Max Act: 8.3725. Min Act: -0.1700
Data Index: 5102385 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8100. Min Range: -8.8100
Max Act: 8.3725. Min Act: -0.1700
Data Index: 7613276 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8100. Min Range: -8.8100
Max Act: 8.3100. Min Act: -0.1700
Data Index: 3086405 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8100. Min Range: -8.8100
Max Act: 8.2475. Min Act: -0.1700
Data Index: 4450352 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8100. Min Range: -8.8100
Max Act: 8.2475. Min Act: -0.1700
Data Index: 5546546 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8100. Min Range: -8.8100
Max Act: 8.2475. Min Act: -0.1700
Data Index: 1194336 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8100. Min Range: -8.8100
Max Act: 8.1225. Min Act: -0.1700
Data Index: 3723373 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8100. Min Range: -8.8100
Max Act: 8.0600. Min Act: -0.1700
Data Index: 3651728 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8100. Min Range: -8.8100
Max Act: 8.0600. Min Act: -0.1700
Data Index: 3417889 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8100. Min Range: -8.8100
Max Act: 8.0600. Min Act: -0.1700
Data Index: 5105247 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8100. Min Range: -8.8100
Max Act: 8.0600. Min Act: -0.1700
Data Index: 3801208 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8100. Min Range: -8.8100
Max Act: 8.0600. Min Act: -0.1700
Data Index: 4808199 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8100. Min Range: -8.8100
Max Act: 8.1225. Min Act: -0.1700
Data Index: 2097347 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8100. Min Range: -8.8100
Max Act: 7.9975. Min Act: -0.1700
Data Index: 4536497 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8100. Min Range: -8.8100
Max Act: 7.9975. Min Act: -0.1700
Data Index: 2576982 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #19