Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5271 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2677. Min Range: -3.2677
Max Act: 3.2677. Min Act: -0.1700
Data Index: 7149465 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2677. Min Range: -3.2677
Max Act: 3.2048. Min Act: -0.1700
Data Index: 7376097 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2677. Min Range: -3.2677
Max Act: 3.1891. Min Act: -0.1700
Data Index: 8311339 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2677. Min Range: -3.2677
Max Act: 3.1734. Min Act: -0.1700
Data Index: 98946 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2677. Min Range: -3.2677
Max Act: 3.1734. Min Act: -0.1700
Data Index: 6574352 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2677. Min Range: -3.2677
Max Act: 3.1734. Min Act: -0.1700
Data Index: 4322068 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2677. Min Range: -3.2677
Max Act: 3.1734. Min Act: -0.1700
Data Index: 3306360 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2677. Min Range: -3.2677
Max Act: 3.1734. Min Act: -0.1700
Data Index: 1921561 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2677. Min Range: -3.2677
Max Act: 3.1734. Min Act: -0.1700
Data Index: 3189941 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2677. Min Range: -3.2677
Max Act: 3.1734. Min Act: -0.1700
Data Index: 1760795 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2677. Min Range: -3.2677
Max Act: 3.1734. Min Act: -0.1700
Data Index: 5552799 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2677. Min Range: -3.2677
Max Act: 3.1734. Min Act: -0.1700
Data Index: 7767137 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2677. Min Range: -3.2677
Max Act: 3.1576. Min Act: -0.1700
Data Index: 4191219 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2677. Min Range: -3.2677
Max Act: 3.1576. Min Act: -0.1700
Data Index: 3644032 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2677. Min Range: -3.2677
Max Act: 3.1576. Min Act: -0.1700
Data Index: 8777799 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2677. Min Range: -3.2677
Max Act: 3.1576. Min Act: -0.1700
Data Index: 1450533 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2677. Min Range: -3.2677
Max Act: 3.1734. Min Act: -0.1700
Data Index: 2592108 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2677. Min Range: -3.2677
Max Act: 3.1576. Min Act: -0.1700
Data Index: 3549065 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2677. Min Range: -3.2677
Max Act: 3.1576. Min Act: -0.1700
Data Index: 7325700 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2677. Min Range: -3.2677
Max Act: 3.1419. Min Act: -0.1700
Data Index: 977189 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19