Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3333 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4027. Min Range: -6.4027
Max Act: 6.4027. Min Act: -0.1700
Data Index: 435585 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4027. Min Range: -6.4027
Max Act: 6.1839. Min Act: -0.1700
Data Index: 1550162 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4027. Min Range: -6.4027
Max Act: 6.1839. Min Act: -0.1700
Data Index: 1786836 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4027. Min Range: -6.4027
Max Act: 6.1527. Min Act: -0.1700
Data Index: 7940234 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4027. Min Range: -6.4027
Max Act: 6.1527. Min Act: -0.1700
Data Index: 3742641 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4027. Min Range: -6.4027
Max Act: 6.1214. Min Act: -0.1700
Data Index: 6700497 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4027. Min Range: -6.4027
Max Act: 6.1214. Min Act: -0.1700
Data Index: 4284805 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4027. Min Range: -6.4027
Max Act: 6.0277. Min Act: -0.1700
Data Index: 4446745 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4027. Min Range: -6.4027
Max Act: 5.9027. Min Act: -0.1700
Data Index: 5395999 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4027. Min Range: -6.4027
Max Act: 5.9027. Min Act: -0.1700
Data Index: 5641317 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4027. Min Range: -6.4027
Max Act: 5.8714. Min Act: -0.1700
Data Index: 2399735 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4027. Min Range: -6.4027
Max Act: 5.8714. Min Act: -0.1700
Data Index: 4365310 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4027. Min Range: -6.4027
Max Act: 5.8714. Min Act: -0.1700
Data Index: 8129792 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4027. Min Range: -6.4027
Max Act: 5.7777. Min Act: -0.1700
Data Index: 710289 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4027. Min Range: -6.4027
Max Act: 5.7777. Min Act: -0.1700
Data Index: 7777414 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4027. Min Range: -6.4027
Max Act: 5.7464. Min Act: -0.1700
Data Index: 3969512 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4027. Min Range: -6.4027
Max Act: 5.7464. Min Act: -0.1700
Data Index: 2210710 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4027. Min Range: -6.4027
Max Act: 5.6839. Min Act: -0.1700
Data Index: 7258729 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4027. Min Range: -6.4027
Max Act: 5.7152. Min Act: -0.1700
Data Index: 5390023 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4027. Min Range: -6.4027
Max Act: 5.6839. Min Act: -0.1700
Data Index: 103847 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19