Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2047 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5057. Min Range: -4.5057
Max Act: 4.5057. Min Act: -0.1700
Data Index: 7953798 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5057. Min Range: -4.5057
Max Act: 4.4744. Min Act: -0.1700
Data Index: 5224279 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5057. Min Range: -4.5057
Max Act: 4.4744. Min Act: -0.1700
Data Index: 1089750 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5057. Min Range: -4.5057
Max Act: 4.4744. Min Act: -0.1700
Data Index: 1714642 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5057. Min Range: -4.5057
Max Act: 4.4744. Min Act: -0.1700
Data Index: 2972497 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5057. Min Range: -4.5057
Max Act: 4.4744. Min Act: -0.1700
Data Index: 4180048 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5057. Min Range: -4.5057
Max Act: 4.4744. Min Act: -0.1700
Data Index: 2870283 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5057. Min Range: -4.5057
Max Act: 4.4744. Min Act: -0.1700
Data Index: 5423985 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5057. Min Range: -4.5057
Max Act: 4.4744. Min Act: -0.1700
Data Index: 5484700 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5057. Min Range: -4.5057
Max Act: 4.4744. Min Act: -0.1700
Data Index: 2178875 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5057. Min Range: -4.5057
Max Act: 4.4744. Min Act: -0.1700
Data Index: 3634906 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5057. Min Range: -4.5057
Max Act: 4.4744. Min Act: -0.1700
Data Index: 6185020 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5057. Min Range: -4.5057
Max Act: 4.4119. Min Act: -0.1700
Data Index: 6810071 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5057. Min Range: -4.5057
Max Act: 4.3807. Min Act: -0.1700
Data Index: 5701571 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5057. Min Range: -4.5057
Max Act: 4.2869. Min Act: -0.1700
Data Index: 8356204 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5057. Min Range: -4.5057
Max Act: 4.2869. Min Act: -0.1700
Data Index: 3019746 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5057. Min Range: -4.5057
Max Act: 4.1932. Min Act: -0.1700
Data Index: 8826461 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5057. Min Range: -4.5057
Max Act: 4.1932. Min Act: -0.1700
Data Index: 5580123 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5057. Min Range: -4.5057
Max Act: 4.1619. Min Act: -0.1700
Data Index: 3123378 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5057. Min Range: -4.5057
Max Act: 4.1932. Min Act: -0.1700
Data Index: 2215319 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19