Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4861 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1123. Min Range: -4.1123
Max Act: 4.1123. Min Act: -0.1700
Data Index: 516752 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1123. Min Range: -4.1123
Max Act: 4.0810. Min Act: -0.1700
Data Index: 7987518 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1123. Min Range: -4.1123
Max Act: 4.0810. Min Act: -0.1700
Data Index: 1829856 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1123. Min Range: -4.1123
Max Act: 4.0497. Min Act: -0.1700
Data Index: 8578431 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1123. Min Range: -4.1123
Max Act: 4.0497. Min Act: -0.1700
Data Index: 8783901 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1123. Min Range: -4.1123
Max Act: 4.0497. Min Act: -0.1700
Data Index: 585952 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1123. Min Range: -4.1123
Max Act: 4.0497. Min Act: -0.1700
Data Index: 3767761 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1123. Min Range: -4.1123
Max Act: 4.0497. Min Act: -0.1700
Data Index: 2671142 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1123. Min Range: -4.1123
Max Act: 4.0185. Min Act: -0.1700
Data Index: 5771794 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1123. Min Range: -4.1123
Max Act: 4.0497. Min Act: -0.1700
Data Index: 5488994 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1123. Min Range: -4.1123
Max Act: 4.0497. Min Act: -0.1700
Data Index: 4931364 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1123. Min Range: -4.1123
Max Act: 4.0185. Min Act: -0.1700
Data Index: 5866050 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1123. Min Range: -4.1123
Max Act: 3.9872. Min Act: -0.1700
Data Index: 5163736 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1123. Min Range: -4.1123
Max Act: 4.0185. Min Act: -0.1700
Data Index: 2026019 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1123. Min Range: -4.1123
Max Act: 4.0185. Min Act: -0.1700
Data Index: 4659959 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1123. Min Range: -4.1123
Max Act: 4.0185. Min Act: -0.1700
Data Index: 4239169 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1123. Min Range: -4.1123
Max Act: 4.0185. Min Act: -0.1700
Data Index: 1607178 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1123. Min Range: -4.1123
Max Act: 4.0185. Min Act: -0.1700
Data Index: 3906109 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1123. Min Range: -4.1123
Max Act: 4.0185. Min Act: -0.1700
Data Index: 3846517 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1123. Min Range: -4.1123
Max Act: 4.0185. Min Act: -0.1700
Data Index: 3432149 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19