Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5562 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7019. Min Range: -6.7019
Max Act: 6.7019. Min Act: -0.1700
Data Index: 8727878 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7019. Min Range: -6.7019
Max Act: 6.7019. Min Act: -0.1700
Data Index: 5241274 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7019. Min Range: -6.7019
Max Act: 6.6082. Min Act: -0.1700
Data Index: 1624748 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7019. Min Range: -6.7019
Max Act: 6.5769. Min Act: -0.1700
Data Index: 1086408 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7019. Min Range: -6.7019
Max Act: 6.5144. Min Act: -0.1700
Data Index: 6416485 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7019. Min Range: -6.7019
Max Act: 6.4519. Min Act: -0.1700
Data Index: 3810809 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7019. Min Range: -6.7019
Max Act: 6.4832. Min Act: -0.1700
Data Index: 7933327 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7019. Min Range: -6.7019
Max Act: 6.4832. Min Act: -0.1700
Data Index: 3929165 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7019. Min Range: -6.7019
Max Act: 6.4519. Min Act: -0.1700
Data Index: 4187663 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7019. Min Range: -6.7019
Max Act: 6.3582. Min Act: -0.1700
Data Index: 7252961 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7019. Min Range: -6.7019
Max Act: 6.3582. Min Act: -0.1700
Data Index: 197273 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7019. Min Range: -6.7019
Max Act: 6.3582. Min Act: -0.1700
Data Index: 6515530 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7019. Min Range: -6.7019
Max Act: 6.3582. Min Act: -0.1700
Data Index: 539195 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7019. Min Range: -6.7019
Max Act: 6.3269. Min Act: -0.1700
Data Index: 6830607 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7019. Min Range: -6.7019
Max Act: 6.2957. Min Act: -0.1700
Data Index: 6217986 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7019. Min Range: -6.7019
Max Act: 6.2957. Min Act: -0.1700
Data Index: 7995891 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7019. Min Range: -6.7019
Max Act: 6.2957. Min Act: -0.1700
Data Index: 69839 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7019. Min Range: -6.7019
Max Act: 6.2957. Min Act: -0.1700
Data Index: 8326125 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7019. Min Range: -6.7019
Max Act: 6.2957. Min Act: -0.1700
Data Index: 2845629 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7019. Min Range: -6.7019
Max Act: 6.2957. Min Act: -0.1700
Data Index: 1799490 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19