Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2104 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7982. Min Range: -6.7982
Max Act: 6.7982. Min Act: -0.1700
Data Index: 6108660 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7982. Min Range: -6.7982
Max Act: 6.4857. Min Act: -0.1700
Data Index: 6565728 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7982. Min Range: -6.7982
Max Act: 6.3295. Min Act: -0.1700
Data Index: 8351551 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7982. Min Range: -6.7982
Max Act: 6.1107. Min Act: -0.1700
Data Index: 4361971 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7982. Min Range: -6.7982
Max Act: 6.0170. Min Act: -0.1700
Data Index: 8168198 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7982. Min Range: -6.7982
Max Act: 5.9857. Min Act: -0.1700
Data Index: 814589 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7982. Min Range: -6.7982
Max Act: 5.9545. Min Act: -0.1700
Data Index: 2643244 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7982. Min Range: -6.7982
Max Act: 5.8295. Min Act: -0.1700
Data Index: 5056355 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7982. Min Range: -6.7982
Max Act: 5.8607. Min Act: -0.1700
Data Index: 6188408 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7982. Min Range: -6.7982
Max Act: 5.7982. Min Act: -0.1700
Data Index: 7712485 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7982. Min Range: -6.7982
Max Act: 5.7670. Min Act: -0.1700
Data Index: 2952227 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7982. Min Range: -6.7982
Max Act: 5.7670. Min Act: -0.1700
Data Index: 1289702 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7982. Min Range: -6.7982
Max Act: 5.7670. Min Act: -0.1700
Data Index: 2224820 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7982. Min Range: -6.7982
Max Act: 5.7670. Min Act: -0.1700
Data Index: 2419914 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7982. Min Range: -6.7982
Max Act: 5.7045. Min Act: -0.1700
Data Index: 1294247 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7982. Min Range: -6.7982
Max Act: 5.6420. Min Act: -0.1700
Data Index: 4746704 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7982. Min Range: -6.7982
Max Act: 5.6732. Min Act: -0.1700
Data Index: 1600077 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7982. Min Range: -6.7982
Max Act: 5.6107. Min Act: -0.1700
Data Index: 6971486 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7982. Min Range: -6.7982
Max Act: 5.6107. Min Act: -0.1700
Data Index: 7927128 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7982. Min Range: -6.7982
Max Act: 5.5795. Min Act: -0.1700
Data Index: 7065781 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19