Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4681 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9462. Min Range: -7.9462
Max Act: 7.9462. Min Act: -0.1700
Data Index: 1103870 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9462. Min Range: -7.9462
Max Act: 7.9462. Min Act: -0.1700
Data Index: 5879922 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9462. Min Range: -7.9462
Max Act: 7.8525. Min Act: -0.1700
Data Index: 3580301 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9462. Min Range: -7.9462
Max Act: 7.8525. Min Act: -0.1700
Data Index: 8592143 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9462. Min Range: -7.9462
Max Act: 7.8212. Min Act: -0.1700
Data Index: 6615653 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9462. Min Range: -7.9462
Max Act: 7.6650. Min Act: -0.1700
Data Index: 2143913 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9462. Min Range: -7.9462
Max Act: 7.6337. Min Act: -0.1700
Data Index: 2147669 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9462. Min Range: -7.9462
Max Act: 7.6337. Min Act: -0.1700
Data Index: 6525268 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9462. Min Range: -7.9462
Max Act: 7.5400. Min Act: -0.1700
Data Index: 3179748 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9462. Min Range: -7.9462
Max Act: 7.5087. Min Act: -0.1700
Data Index: 2279221 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9462. Min Range: -7.9462
Max Act: 7.5087. Min Act: -0.1700
Data Index: 5717698 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9462. Min Range: -7.9462
Max Act: 7.5087. Min Act: -0.1700
Data Index: 5596908 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9462. Min Range: -7.9462
Max Act: 7.5087. Min Act: -0.1700
Data Index: 5390333 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9462. Min Range: -7.9462
Max Act: 7.4775. Min Act: -0.1700
Data Index: 4013126 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9462. Min Range: -7.9462
Max Act: 7.4775. Min Act: -0.1700
Data Index: 1135223 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9462. Min Range: -7.9462
Max Act: 7.4775. Min Act: -0.1700
Data Index: 7494962 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9462. Min Range: -7.9462
Max Act: 7.4462. Min Act: -0.1700
Data Index: 5965135 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9462. Min Range: -7.9462
Max Act: 7.4462. Min Act: -0.1700
Data Index: 7030030 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9462. Min Range: -7.9462
Max Act: 7.4150. Min Act: -0.1700
Data Index: 2154029 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9462. Min Range: -7.9462
Max Act: 7.3837. Min Act: -0.1700
Data Index: 193571 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #19