Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1485 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6909. Min Range: -5.6909
Max Act: 5.6909. Min Act: -0.1700
Data Index: 7789712 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6909. Min Range: -5.6909
Max Act: 5.6909. Min Act: -0.1700
Data Index: 3496057 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6909. Min Range: -5.6909
Max Act: 5.6909. Min Act: -0.1700
Data Index: 6360618 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6909. Min Range: -5.6909
Max Act: 5.5347. Min Act: -0.1700
Data Index: 8477676 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6909. Min Range: -5.6909
Max Act: 5.5034. Min Act: -0.1700
Data Index: 914553 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6909. Min Range: -5.6909
Max Act: 5.5347. Min Act: -0.1700
Data Index: 7502171 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6909. Min Range: -5.6909
Max Act: 5.5034. Min Act: -0.1700
Data Index: 8014807 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6909. Min Range: -5.6909
Max Act: 5.5347. Min Act: -0.1700
Data Index: 6360621 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6909. Min Range: -5.6909
Max Act: 5.5347. Min Act: -0.1700
Data Index: 7502156 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6909. Min Range: -5.6909
Max Act: 5.5034. Min Act: -0.1700
Data Index: 8340692 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6909. Min Range: -5.6909
Max Act: 5.5034. Min Act: -0.1700
Data Index: 7579496 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6909. Min Range: -5.6909
Max Act: 5.5034. Min Act: -0.1700
Data Index: 6255299 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6909. Min Range: -5.6909
Max Act: 5.4409. Min Act: -0.1700
Data Index: 3496052 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6909. Min Range: -5.6909
Max Act: 5.4409. Min Act: -0.1700
Data Index: 3496050 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6909. Min Range: -5.6909
Max Act: 5.4722. Min Act: -0.1700
Data Index: 3700803 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6909. Min Range: -5.6909
Max Act: 5.4409. Min Act: -0.1700
Data Index: 3349133 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6909. Min Range: -5.6909
Max Act: 5.4097. Min Act: -0.1700
Data Index: 6255301 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6909. Min Range: -5.6909
Max Act: 5.3784. Min Act: -0.1700
Data Index: 603088 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6909. Min Range: -5.6909
Max Act: 5.4097. Min Act: -0.1700
Data Index: 521229 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6909. Min Range: -5.6909
Max Act: 5.4097. Min Act: -0.1700
Data Index: 7789727 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19