Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3631 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1329. Min Range: -7.1329
Max Act: 7.1329. Min Act: -0.1700
Data Index: 5525010 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1329. Min Range: -7.1329
Max Act: 7.1016. Min Act: -0.1700
Data Index: 3825579 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1329. Min Range: -7.1329
Max Act: 6.4766. Min Act: -0.1700
Data Index: 6484536 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1329. Min Range: -7.1329
Max Act: 6.1329. Min Act: -0.1700
Data Index: 2093194 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1329. Min Range: -7.1329
Max Act: 5.9766. Min Act: -0.1700
Data Index: 6286240 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1329. Min Range: -7.1329
Max Act: 5.9766. Min Act: -0.1700
Data Index: 2569676 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1329. Min Range: -7.1329
Max Act: 5.9141. Min Act: -0.1700
Data Index: 3525646 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1329. Min Range: -7.1329
Max Act: 5.9141. Min Act: -0.1700
Data Index: 7663503 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1329. Min Range: -7.1329
Max Act: 5.8204. Min Act: -0.1700
Data Index: 1306658 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1329. Min Range: -7.1329
Max Act: 5.7891. Min Act: -0.1700
Data Index: 3525641 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1329. Min Range: -7.1329
Max Act: 5.6954. Min Act: -0.1700
Data Index: 3554523 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1329. Min Range: -7.1329
Max Act: 5.6954. Min Act: -0.1700
Data Index: 8790147 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1329. Min Range: -7.1329
Max Act: 5.6641. Min Act: -0.1700
Data Index: 1618601 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1329. Min Range: -7.1329
Max Act: 5.6329. Min Act: -0.1700
Data Index: 1342541 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1329. Min Range: -7.1329
Max Act: 5.6329. Min Act: -0.1698
Data Index: 252108 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1329. Min Range: -7.1329
Max Act: 5.6329. Min Act: -0.1700
Data Index: 6007045 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1329. Min Range: -7.1329
Max Act: 5.6329. Min Act: -0.1700
Data Index: 3525632 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1329. Min Range: -7.1329
Max Act: 5.6329. Min Act: -0.1699
Data Index: 5451458 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1329. Min Range: -7.1329
Max Act: 5.6329. Min Act: -0.1700
Data Index: 1618599 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1329. Min Range: -7.1329
Max Act: 5.6016. Min Act: -0.1700
Data Index: 3525644 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19