Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4925 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 31.9968. Min Range: -31.9968
Max Act: 31.9968. Min Act: -0.1700
Data Index: 8412029 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 31.9968. Min Range: -31.9968
Max Act: 31.7468. Min Act: -0.1700
Data Index: 3255319 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 31.9968. Min Range: -31.9968
Max Act: 31.4968. Min Act: -0.1700
Data Index: 8008358 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 31.9968. Min Range: -31.9968
Max Act: 31.6218. Min Act: -0.1700
Data Index: 359719 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 31.9968. Min Range: -31.9968
Max Act: 31.4968. Min Act: -0.1700
Data Index: 555914 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 31.9968. Min Range: -31.9968
Max Act: 31.4968. Min Act: -0.1700
Data Index: 4249300 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 31.9968. Min Range: -31.9968
Max Act: 31.3718. Min Act: -0.1700
Data Index: 1171255 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 31.9968. Min Range: -31.9968
Max Act: 31.4968. Min Act: -0.1700
Data Index: 2627660 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 31.9968. Min Range: -31.9968
Max Act: 31.4968. Min Act: -0.1700
Data Index: 1314989 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 31.9968. Min Range: -31.9968
Max Act: 31.4968. Min Act: -0.1700
Data Index: 5810259 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 31.9968. Min Range: -31.9968
Max Act: 31.3718. Min Act: -0.1700
Data Index: 7092774 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 31.9968. Min Range: -31.9968
Max Act: 31.4968. Min Act: -0.1700
Data Index: 1063221 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 31.9968. Min Range: -31.9968
Max Act: 31.3718. Min Act: -0.1700
Data Index: 8681469 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 31.9968. Min Range: -31.9968
Max Act: 31.3718. Min Act: -0.1700
Data Index: 2349243 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 31.9968. Min Range: -31.9968
Max Act: 31.3718. Min Act: -0.1700
Data Index: 1536394 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 31.9968. Min Range: -31.9968
Max Act: 31.3718. Min Act: -0.1696
Data Index: 5967855 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 31.9968. Min Range: -31.9968
Max Act: 31.3718. Min Act: -0.1700
Data Index: 2210267 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 31.9968. Min Range: -31.9968
Max Act: 31.3718. Min Act: -0.1700
Data Index: 1220650 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 31.9968. Min Range: -31.9968
Max Act: 31.3718. Min Act: -0.1700
Data Index: 2063667 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 31.9968. Min Range: -31.9968
Max Act: 31.2468. Min Act: -0.1700
Data Index: 2795525 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19