Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3299 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9234. Min Range: -4.9234
Max Act: 4.9234. Min Act: -0.1700
Data Index: 5061625 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9234. Min Range: -4.9234
Max Act: 4.9234. Min Act: -0.1700
Data Index: 6924615 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9234. Min Range: -4.9234
Max Act: 4.9234. Min Act: -0.1700
Data Index: 3079004 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9234. Min Range: -4.9234
Max Act: 4.9234. Min Act: -0.1700
Data Index: 5288360 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9234. Min Range: -4.9234
Max Act: 4.8922. Min Act: -0.1700
Data Index: 3096186 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9234. Min Range: -4.9234
Max Act: 4.8922. Min Act: -0.1700
Data Index: 3674296 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9234. Min Range: -4.9234
Max Act: 4.8922. Min Act: -0.1700
Data Index: 7444932 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9234. Min Range: -4.9234
Max Act: 4.8922. Min Act: -0.1700
Data Index: 5651261 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9234. Min Range: -4.9234
Max Act: 4.8922. Min Act: -0.1700
Data Index: 5665164 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9234. Min Range: -4.9234
Max Act: 4.8922. Min Act: -0.1700
Data Index: 6393366 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9234. Min Range: -4.9234
Max Act: 4.8609. Min Act: -0.1700
Data Index: 3499566 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9234. Min Range: -4.9234
Max Act: 4.8609. Min Act: -0.1700
Data Index: 7220054 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9234. Min Range: -4.9234
Max Act: 4.8609. Min Act: -0.1700
Data Index: 6846697 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9234. Min Range: -4.9234
Max Act: 4.8609. Min Act: -0.1700
Data Index: 3675909 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9234. Min Range: -4.9234
Max Act: 4.8609. Min Act: -0.1700
Data Index: 6571355 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9234. Min Range: -4.9234
Max Act: 4.8609. Min Act: -0.1700
Data Index: 3192096 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9234. Min Range: -4.9234
Max Act: 4.8609. Min Act: -0.1700
Data Index: 5650138 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9234. Min Range: -4.9234
Max Act: 4.8609. Min Act: -0.1700
Data Index: 5626880 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9234. Min Range: -4.9234
Max Act: 4.8609. Min Act: -0.1700
Data Index: 1479209 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9234. Min Range: -4.9234
Max Act: 4.8609. Min Act: -0.1700
Data Index: 2786038 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19