Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 18 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1754. Min Range: -6.1754
Max Act: 6.1754. Min Act: -0.1700
Data Index: 218357 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1754. Min Range: -6.1754
Max Act: 5.9879. Min Act: -0.1700
Data Index: 4127766 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1754. Min Range: -6.1754
Max Act: 5.8317. Min Act: -0.1700
Data Index: 4682653 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1754. Min Range: -6.1754
Max Act: 5.8004. Min Act: -0.1700
Data Index: 202459 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1754. Min Range: -6.1754
Max Act: 5.7692. Min Act: -0.1700
Data Index: 3220565 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1754. Min Range: -6.1754
Max Act: 5.7379. Min Act: -0.1700
Data Index: 8022877 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1754. Min Range: -6.1754
Max Act: 5.7379. Min Act: -0.1700
Data Index: 6681363 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1754. Min Range: -6.1754
Max Act: 5.6754. Min Act: -0.1700
Data Index: 3387589 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1754. Min Range: -6.1754
Max Act: 5.7067. Min Act: -0.1700
Data Index: 1790644 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1754. Min Range: -6.1754
Max Act: 5.7067. Min Act: -0.1700
Data Index: 7987715 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1754. Min Range: -6.1754
Max Act: 5.7067. Min Act: -0.1700
Data Index: 7472027 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1754. Min Range: -6.1754
Max Act: 5.7067. Min Act: -0.1700
Data Index: 8095471 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1754. Min Range: -6.1754
Max Act: 5.7067. Min Act: -0.1700
Data Index: 85768 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1754. Min Range: -6.1754
Max Act: 5.6442. Min Act: -0.1700
Data Index: 4786199 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1754. Min Range: -6.1754
Max Act: 5.6442. Min Act: -0.1700
Data Index: 4639658 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1754. Min Range: -6.1754
Max Act: 5.6442. Min Act: -0.1700
Data Index: 5704162 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1754. Min Range: -6.1754
Max Act: 5.6442. Min Act: -0.1700
Data Index: 7652474 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1754. Min Range: -6.1754
Max Act: 5.6129. Min Act: -0.1700
Data Index: 4211650 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1754. Min Range: -6.1754
Max Act: 5.6129. Min Act: -0.1700
Data Index: 7486380 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1754. Min Range: -6.1754
Max Act: 5.6129. Min Act: -0.1700
Data Index: 5853365 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #19