Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2046 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5039. Min Range: -5.5039
Max Act: 5.5039. Min Act: -0.1700
Data Index: 5120476 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5039. Min Range: -5.5039
Max Act: 5.4414. Min Act: -0.1700
Data Index: 7685419 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5039. Min Range: -5.5039
Max Act: 5.4102. Min Act: -0.1700
Data Index: 2881308 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5039. Min Range: -5.5039
Max Act: 5.4102. Min Act: -0.1700
Data Index: 3705556 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5039. Min Range: -5.5039
Max Act: 5.4102. Min Act: -0.1700
Data Index: 3987155 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5039. Min Range: -5.5039
Max Act: 5.3789. Min Act: -0.1700
Data Index: 3613425 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5039. Min Range: -5.5039
Max Act: 5.3789. Min Act: -0.1700
Data Index: 2874941 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5039. Min Range: -5.5039
Max Act: 5.3789. Min Act: -0.1700
Data Index: 6926287 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5039. Min Range: -5.5039
Max Act: 5.3477. Min Act: -0.1700
Data Index: 7975406 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5039. Min Range: -5.5039
Max Act: 5.3477. Min Act: -0.1700
Data Index: 2895764 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5039. Min Range: -5.5039
Max Act: 5.3477. Min Act: -0.1700
Data Index: 5753464 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5039. Min Range: -5.5039
Max Act: 5.3789. Min Act: -0.1700
Data Index: 2922361 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5039. Min Range: -5.5039
Max Act: 5.3477. Min Act: -0.1700
Data Index: 6210875 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5039. Min Range: -5.5039
Max Act: 5.3164. Min Act: -0.1700
Data Index: 2074172 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5039. Min Range: -5.5039
Max Act: 5.3164. Min Act: -0.1700
Data Index: 6759054 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5039. Min Range: -5.5039
Max Act: 5.3164. Min Act: -0.1700
Data Index: 6455410 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5039. Min Range: -5.5039
Max Act: 5.3164. Min Act: -0.1700
Data Index: 3838570 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5039. Min Range: -5.5039
Max Act: 5.2852. Min Act: -0.1700
Data Index: 4691661 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5039. Min Range: -5.5039
Max Act: 5.2852. Min Act: -0.1699
Data Index: 2454072 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5039. Min Range: -5.5039
Max Act: 5.2539. Min Act: -0.1700
Data Index: 3495564 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #19