Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2882 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1093. Min Range: -6.1093
Max Act: 6.1093. Min Act: -0.1700
Data Index: 1154017 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1093. Min Range: -6.1093
Max Act: 5.9843. Min Act: -0.1700
Data Index: 1654223 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1093. Min Range: -6.1093
Max Act: 5.8906. Min Act: -0.1700
Data Index: 8477632 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1093. Min Range: -6.1093
Max Act: 5.8906. Min Act: -0.1700
Data Index: 5922514 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1093. Min Range: -6.1093
Max Act: 5.8593. Min Act: -0.1700
Data Index: 5706783 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1093. Min Range: -6.1093
Max Act: 5.7343. Min Act: -0.1700
Data Index: 5706787 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1093. Min Range: -6.1093
Max Act: 5.7031. Min Act: -0.1700
Data Index: 3217597 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1093. Min Range: -6.1093
Max Act: 5.7031. Min Act: -0.1700
Data Index: 2084145 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1093. Min Range: -6.1093
Max Act: 5.7031. Min Act: -0.1700
Data Index: 7925628 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1093. Min Range: -6.1093
Max Act: 5.7031. Min Act: -0.1700
Data Index: 5284645 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1093. Min Range: -6.1093
Max Act: 5.7031. Min Act: -0.1700
Data Index: 2401414 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1093. Min Range: -6.1093
Max Act: 5.6718. Min Act: -0.1700
Data Index: 7207905 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1093. Min Range: -6.1093
Max Act: 5.6718. Min Act: -0.1700
Data Index: 7706764 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1093. Min Range: -6.1093
Max Act: 5.6718. Min Act: -0.1700
Data Index: 4286761 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1093. Min Range: -6.1093
Max Act: 5.6406. Min Act: -0.1700
Data Index: 4259506 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1093. Min Range: -6.1093
Max Act: 5.6718. Min Act: -0.1700
Data Index: 6708153 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1093. Min Range: -6.1093
Max Act: 5.6718. Min Act: -0.1700
Data Index: 7321183 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1093. Min Range: -6.1093
Max Act: 5.6093. Min Act: -0.1700
Data Index: 3927834 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1093. Min Range: -6.1093
Max Act: 5.6406. Min Act: -0.1700
Data Index: 1853212 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1093. Min Range: -6.1093
Max Act: 5.6093. Min Act: -0.1700
Data Index: 1502595 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19