Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3624 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9790. Min Range: -4.9790
Max Act: 4.9790. Min Act: -0.1700
Data Index: 1084839 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9790. Min Range: -4.9790
Max Act: 4.8853. Min Act: -0.1700
Data Index: 176731 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9790. Min Range: -4.9790
Max Act: 4.8540. Min Act: -0.1700
Data Index: 1933546 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9790. Min Range: -4.9790
Max Act: 4.8540. Min Act: -0.1700
Data Index: 6024093 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9790. Min Range: -4.9790
Max Act: 4.8540. Min Act: -0.1700
Data Index: 6896898 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9790. Min Range: -4.9790
Max Act: 4.7603. Min Act: -0.1700
Data Index: 6629713 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9790. Min Range: -4.9790
Max Act: 4.6353. Min Act: -0.1700
Data Index: 4084450 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9790. Min Range: -4.9790
Max Act: 4.6353. Min Act: -0.1700
Data Index: 3845687 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9790. Min Range: -4.9790
Max Act: 4.6665. Min Act: -0.1700
Data Index: 1285263 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9790. Min Range: -4.9790
Max Act: 4.6353. Min Act: -0.1700
Data Index: 6288268 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9790. Min Range: -4.9790
Max Act: 4.6040. Min Act: -0.1700
Data Index: 5707470 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9790. Min Range: -4.9790
Max Act: 4.6040. Min Act: -0.1700
Data Index: 8484097 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9790. Min Range: -4.9790
Max Act: 4.6040. Min Act: -0.1700
Data Index: 5962712 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9790. Min Range: -4.9790
Max Act: 4.5728. Min Act: -0.1700
Data Index: 8187267 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9790. Min Range: -4.9790
Max Act: 4.5728. Min Act: -0.1700
Data Index: 1438506 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9790. Min Range: -4.9790
Max Act: 4.5728. Min Act: -0.1700
Data Index: 8716647 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9790. Min Range: -4.9790
Max Act: 4.5728. Min Act: -0.1700
Data Index: 6291046 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9790. Min Range: -4.9790
Max Act: 4.5415. Min Act: -0.1700
Data Index: 7721513 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9790. Min Range: -4.9790
Max Act: 4.5415. Min Act: -0.1700
Data Index: 8320202 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9790. Min Range: -4.9790
Max Act: 4.5415. Min Act: -0.1700
Data Index: 156031 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19