Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2217 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.1134. Min Range: -1.1134
Max Act: 1.1134. Min Act: -0.1700
Data Index: 5850681 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1134. Min Range: -1.1134
Max Act: 1.0260. Min Act: -0.1700
Data Index: 5157282 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1134. Min Range: -1.1134
Max Act: 0.9739. Min Act: -0.1700
Data Index: 3609095 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1134. Min Range: -1.1134
Max Act: 0.9739. Min Act: -0.1699
Data Index: 2203666 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1134. Min Range: -1.1134
Max Act: 0.9739. Min Act: -0.1700
Data Index: 5045068 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1134. Min Range: -1.1134
Max Act: 0.9394. Min Act: -0.1700
Data Index: 4368542 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1134. Min Range: -1.1134
Max Act: 0.9222. Min Act: -0.1700
Data Index: 5021430 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1134. Min Range: -1.1134
Max Act: 0.9222. Min Act: -0.1700
Data Index: 6666416 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1134. Min Range: -1.1134
Max Act: 0.9222. Min Act: -0.1700
Data Index: 4839087 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1134. Min Range: -1.1134
Max Act: 0.8880. Min Act: -0.1700
Data Index: 8711725 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1134. Min Range: -1.1134
Max Act: 0.8709. Min Act: -0.1700
Data Index: 6138872 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1134. Min Range: -1.1134
Max Act: 0.8539. Min Act: -0.1700
Data Index: 7325972 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1134. Min Range: -1.1134
Max Act: 0.8539. Min Act: -0.1700
Data Index: 267666 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1134. Min Range: -1.1134
Max Act: 0.8370. Min Act: -0.1700
Data Index: 4839091 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1134. Min Range: -1.1134
Max Act: 0.8455. Min Act: -0.1700
Data Index: 2269763 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1134. Min Range: -1.1134
Max Act: 0.8455. Min Act: -0.1700
Data Index: 3114184 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1134. Min Range: -1.1134
Max Act: 0.8117. Min Act: -0.1700
Data Index: 7774309 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1134. Min Range: -1.1134
Max Act: 0.8201. Min Act: -0.1700
Data Index: 4387350 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1134. Min Range: -1.1134
Max Act: 0.8117. Min Act: -0.1700
Data Index: 820947 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1134. Min Range: -1.1134
Max Act: 0.7949. Min Act: -0.1700
Data Index: 2081344 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #19