Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2278 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9953. Min Range: -4.9953
Max Act: 4.9953. Min Act: -0.1700
Data Index: 535390 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9953. Min Range: -4.9953
Max Act: 4.8703. Min Act: -0.1700
Data Index: 3781182 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9953. Min Range: -4.9953
Max Act: 4.8703. Min Act: -0.1700
Data Index: 4892433 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9953. Min Range: -4.9953
Max Act: 4.7765. Min Act: -0.1700
Data Index: 8083612 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9953. Min Range: -4.9953
Max Act: 4.7765. Min Act: -0.1700
Data Index: 5320066 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9953. Min Range: -4.9953
Max Act: 4.7765. Min Act: -0.1700
Data Index: 2864412 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9953. Min Range: -4.9953
Max Act: 4.7453. Min Act: -0.1700
Data Index: 4190237 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9953. Min Range: -4.9953
Max Act: 4.7140. Min Act: -0.1700
Data Index: 1097942 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9953. Min Range: -4.9953
Max Act: 4.7453. Min Act: -0.1700
Data Index: 8558943 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9953. Min Range: -4.9953
Max Act: 4.7140. Min Act: -0.1700
Data Index: 4432025 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9953. Min Range: -4.9953
Max Act: 4.7140. Min Act: -0.1700
Data Index: 5038434 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9953. Min Range: -4.9953
Max Act: 4.6515. Min Act: -0.1700
Data Index: 570106 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9953. Min Range: -4.9953
Max Act: 4.6828. Min Act: -0.1700
Data Index: 5580580 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9953. Min Range: -4.9953
Max Act: 4.6828. Min Act: -0.1700
Data Index: 3195498 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9953. Min Range: -4.9953
Max Act: 4.6828. Min Act: -0.1700
Data Index: 2611765 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9953. Min Range: -4.9953
Max Act: 4.7140. Min Act: -0.1700
Data Index: 5067607 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9953. Min Range: -4.9953
Max Act: 4.6515. Min Act: -0.1700
Data Index: 2686037 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9953. Min Range: -4.9953
Max Act: 4.6203. Min Act: -0.1700
Data Index: 5241422 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9953. Min Range: -4.9953
Max Act: 4.6515. Min Act: -0.1700
Data Index: 748488 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9953. Min Range: -4.9953
Max Act: 4.6203. Min Act: -0.1700
Data Index: 4834979 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19