Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2099 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5476. Min Range: -6.5476
Max Act: 6.5476. Min Act: -0.1700
Data Index: 1067251 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5476. Min Range: -6.5476
Max Act: 6.2351. Min Act: -0.1700
Data Index: 1057732 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5476. Min Range: -6.5476
Max Act: 5.9851. Min Act: -0.1700
Data Index: 3280065 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5476. Min Range: -6.5476
Max Act: 5.9851. Min Act: -0.1700
Data Index: 7113955 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5476. Min Range: -6.5476
Max Act: 5.9226. Min Act: -0.1700
Data Index: 1937548 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5476. Min Range: -6.5476
Max Act: 5.8914. Min Act: -0.1700
Data Index: 7203584 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5476. Min Range: -6.5476
Max Act: 5.8914. Min Act: -0.1700
Data Index: 4577411 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5476. Min Range: -6.5476
Max Act: 5.8601. Min Act: -0.1700
Data Index: 6322949 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5476. Min Range: -6.5476
Max Act: 5.8289. Min Act: -0.1700
Data Index: 8475312 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5476. Min Range: -6.5476
Max Act: 5.8601. Min Act: -0.1700
Data Index: 2221436 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5476. Min Range: -6.5476
Max Act: 5.8601. Min Act: -0.1700
Data Index: 837323 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5476. Min Range: -6.5476
Max Act: 5.8289. Min Act: -0.1700
Data Index: 2653169 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5476. Min Range: -6.5476
Max Act: 5.7976. Min Act: -0.1700
Data Index: 1937547 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5476. Min Range: -6.5476
Max Act: 5.7976. Min Act: -0.1700
Data Index: 502526 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5476. Min Range: -6.5476
Max Act: 5.7664. Min Act: -0.1700
Data Index: 4053547 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5476. Min Range: -6.5476
Max Act: 5.7664. Min Act: -0.1700
Data Index: 4032740 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5476. Min Range: -6.5476
Max Act: 5.7664. Min Act: -0.1700
Data Index: 1283236 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5476. Min Range: -6.5476
Max Act: 5.7664. Min Act: -0.1700
Data Index: 3645946 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5476. Min Range: -6.5476
Max Act: 5.7351. Min Act: -0.1700
Data Index: 5076900 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5476. Min Range: -6.5476
Max Act: 5.7039. Min Act: -0.1700
Data Index: 1073073 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #19