Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2754 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7167. Min Range: -7.7167
Max Act: 7.7167. Min Act: -0.1700
Data Index: 1908509 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7167. Min Range: -7.7167
Max Act: 7.7167. Min Act: -0.1700
Data Index: 534748 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7167. Min Range: -7.7167
Max Act: 7.6542. Min Act: -0.1700
Data Index: 1988192 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7167. Min Range: -7.7167
Max Act: 7.5917. Min Act: -0.1700
Data Index: 2580212 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7167. Min Range: -7.7167
Max Act: 7.5917. Min Act: -0.1700
Data Index: 5803786 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7167. Min Range: -7.7167
Max Act: 7.5917. Min Act: -0.1700
Data Index: 8585472 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7167. Min Range: -7.7167
Max Act: 7.5292. Min Act: -0.1700
Data Index: 3933 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7167. Min Range: -7.7167
Max Act: 7.5292. Min Act: -0.1700
Data Index: 3715842 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7167. Min Range: -7.7167
Max Act: 7.4667. Min Act: -0.1700
Data Index: 5994535 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7167. Min Range: -7.7167
Max Act: 7.4667. Min Act: -0.1700
Data Index: 7969387 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7167. Min Range: -7.7167
Max Act: 7.4354. Min Act: -0.1700
Data Index: 8646087 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7167. Min Range: -7.7167
Max Act: 7.4042. Min Act: -0.1700
Data Index: 745847 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7167. Min Range: -7.7167
Max Act: 7.4042. Min Act: -0.1700
Data Index: 4286490 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7167. Min Range: -7.7167
Max Act: 7.4042. Min Act: -0.1700
Data Index: 7222318 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7167. Min Range: -7.7167
Max Act: 7.3729. Min Act: -0.1700
Data Index: 51753 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7167. Min Range: -7.7167
Max Act: 7.4042. Min Act: -0.1700
Data Index: 2697184 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7167. Min Range: -7.7167
Max Act: 7.3104. Min Act: -0.1700
Data Index: 1571989 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7167. Min Range: -7.7167
Max Act: 7.2792. Min Act: -0.1700
Data Index: 5961723 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7167. Min Range: -7.7167
Max Act: 7.2792. Min Act: -0.1700
Data Index: 4124663 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7167. Min Range: -7.7167
Max Act: 7.2479. Min Act: -0.1700
Data Index: 5099268 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #19