Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3651 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7684. Min Range: -5.7684
Max Act: 5.7684. Min Act: -0.1700
Data Index: 1012953 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7684. Min Range: -5.7684
Max Act: 5.6746. Min Act: -0.1700
Data Index: 1644227 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7684. Min Range: -5.7684
Max Act: 5.6434. Min Act: -0.1700
Data Index: 8254703 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7684. Min Range: -5.7684
Max Act: 5.6434. Min Act: -0.1700
Data Index: 2291545 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7684. Min Range: -5.7684
Max Act: 5.6434. Min Act: -0.1700
Data Index: 1694714 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7684. Min Range: -5.7684
Max Act: 5.5184. Min Act: -0.1700
Data Index: 8252154 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7684. Min Range: -5.7684
Max Act: 5.4871. Min Act: -0.1700
Data Index: 5311546 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7684. Min Range: -5.7684
Max Act: 5.4871. Min Act: -0.1700
Data Index: 4202747 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7684. Min Range: -5.7684
Max Act: 5.4559. Min Act: -0.1700
Data Index: 495472 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7684. Min Range: -5.7684
Max Act: 5.4559. Min Act: -0.1700
Data Index: 7485144 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7684. Min Range: -5.7684
Max Act: 5.4559. Min Act: -0.1700
Data Index: 501221 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7684. Min Range: -5.7684
Max Act: 5.4246. Min Act: -0.1700
Data Index: 7080265 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7684. Min Range: -5.7684
Max Act: 5.3934. Min Act: -0.1700
Data Index: 7690334 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7684. Min Range: -5.7684
Max Act: 5.3934. Min Act: -0.1700
Data Index: 676365 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7684. Min Range: -5.7684
Max Act: 5.3934. Min Act: -0.1700
Data Index: 6389599 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7684. Min Range: -5.7684
Max Act: 5.3934. Min Act: -0.1700
Data Index: 5278689 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7684. Min Range: -5.7684
Max Act: 5.3621. Min Act: -0.1700
Data Index: 1809385 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7684. Min Range: -5.7684
Max Act: 5.3934. Min Act: -0.1700
Data Index: 7948796 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7684. Min Range: -5.7684
Max Act: 5.3309. Min Act: -0.1700
Data Index: 5050255 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7684. Min Range: -5.7684
Max Act: 5.3621. Min Act: -0.1700
Data Index: 8238938 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19