Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2719 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9116. Min Range: -7.9116
Max Act: 7.9116. Min Act: -0.1700
Data Index: 3245537 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9116. Min Range: -7.9116
Max Act: 7.8491. Min Act: -0.1700
Data Index: 5647338 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9116. Min Range: -7.9116
Max Act: 7.4116. Min Act: -0.1700
Data Index: 7925219 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9116. Min Range: -7.9116
Max Act: 7.2866. Min Act: -0.1700
Data Index: 5425866 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9116. Min Range: -7.9116
Max Act: 7.2866. Min Act: -0.1700
Data Index: 3305033 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9116. Min Range: -7.9116
Max Act: 7.2241. Min Act: -0.1700
Data Index: 1610056 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9116. Min Range: -7.9116
Max Act: 7.1304. Min Act: -0.1700
Data Index: 1854124 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9116. Min Range: -7.9116
Max Act: 7.1616. Min Act: -0.1700
Data Index: 813001 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9116. Min Range: -7.9116
Max Act: 7.1304. Min Act: -0.1700
Data Index: 215424 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9116. Min Range: -7.9116
Max Act: 7.1304. Min Act: -0.1700
Data Index: 6199980 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9116. Min Range: -7.9116
Max Act: 7.0679. Min Act: -0.1700
Data Index: 1794726 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9116. Min Range: -7.9116
Max Act: 7.0679. Min Act: -0.1700
Data Index: 1152379 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9116. Min Range: -7.9116
Max Act: 7.0679. Min Act: -0.1700
Data Index: 8583679 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9116. Min Range: -7.9116
Max Act: 7.0679. Min Act: -0.1700
Data Index: 4926084 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9116. Min Range: -7.9116
Max Act: 7.0366. Min Act: -0.1700
Data Index: 6901498 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9116. Min Range: -7.9116
Max Act: 7.0679. Min Act: -0.1700
Data Index: 2233253 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9116. Min Range: -7.9116
Max Act: 7.0054. Min Act: -0.1700
Data Index: 2608226 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9116. Min Range: -7.9116
Max Act: 6.9741. Min Act: -0.1700
Data Index: 694692 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9116. Min Range: -7.9116
Max Act: 7.0054. Min Act: -0.1700
Data Index: 3998057 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9116. Min Range: -7.9116
Max Act: 7.0054. Min Act: -0.1700
Data Index: 247365 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19