Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1966 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.4492. Min Act: -0.1700
Data Index: 7231639 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.3867. Min Act: -0.1699
Data Index: 1044967 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.3867. Min Act: -0.1700
Data Index: 1748399 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.3867. Min Act: -0.1700
Data Index: 1619140 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.3554. Min Act: -0.1700
Data Index: 3301976 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.3241. Min Act: -0.1700
Data Index: 4796468 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.2929. Min Act: -0.1700
Data Index: 1619136 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.2929. Min Act: -0.1700
Data Index: 478221 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.2929. Min Act: -0.1700
Data Index: 8759285 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.2929. Min Act: -0.1700
Data Index: 4972538 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.2929. Min Act: -0.1700
Data Index: 3785043 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.2929. Min Act: -0.1700
Data Index: 2472829 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.2304. Min Act: -0.1700
Data Index: 8315973 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.2304. Min Act: -0.1700
Data Index: 6510214 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.2304. Min Act: -0.1700
Data Index: 1619132 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.2304. Min Act: -0.1700
Data Index: 8330333 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.2304. Min Act: -0.1700
Data Index: 2438505 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.1991. Min Act: -0.1700
Data Index: 6903665 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.1991. Min Act: -0.1700
Data Index: 140706 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.1991. Min Act: -0.1700
Data Index: 5664249 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19