Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2671 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8158. Min Range: -5.8158
Max Act: 5.8158. Min Act: -0.1700
Data Index: 5087227 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8158. Min Range: -5.8158
Max Act: 5.4720. Min Act: -0.1700
Data Index: 7074384 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8158. Min Range: -5.8158
Max Act: 5.4408. Min Act: -0.1700
Data Index: 6409388 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8158. Min Range: -5.8158
Max Act: 5.4408. Min Act: -0.1700
Data Index: 358803 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8158. Min Range: -5.8158
Max Act: 5.4095. Min Act: -0.1700
Data Index: 4335081 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8158. Min Range: -5.8158
Max Act: 5.4408. Min Act: -0.1700
Data Index: 4936071 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8158. Min Range: -5.8158
Max Act: 5.3470. Min Act: -0.1700
Data Index: 8587714 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8158. Min Range: -5.8158
Max Act: 5.3783. Min Act: -0.1700
Data Index: 930572 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8158. Min Range: -5.8158
Max Act: 5.3783. Min Act: -0.1700
Data Index: 8448982 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8158. Min Range: -5.8158
Max Act: 5.3783. Min Act: -0.1700
Data Index: 1810177 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8158. Min Range: -5.8158
Max Act: 5.3470. Min Act: -0.1700
Data Index: 8033881 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8158. Min Range: -5.8158
Max Act: 5.4095. Min Act: -0.1700
Data Index: 452842 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8158. Min Range: -5.8158
Max Act: 5.3158. Min Act: -0.1700
Data Index: 7559090 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8158. Min Range: -5.8158
Max Act: 5.3470. Min Act: -0.1700
Data Index: 895371 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8158. Min Range: -5.8158
Max Act: 5.3470. Min Act: -0.1700
Data Index: 6873389 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8158. Min Range: -5.8158
Max Act: 5.3470. Min Act: -0.1700
Data Index: 1911346 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8158. Min Range: -5.8158
Max Act: 5.3470. Min Act: -0.1700
Data Index: 5572592 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8158. Min Range: -5.8158
Max Act: 5.3470. Min Act: -0.1700
Data Index: 5838239 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8158. Min Range: -5.8158
Max Act: 5.2845. Min Act: -0.1700
Data Index: 1905132 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8158. Min Range: -5.8158
Max Act: 5.3158. Min Act: -0.1700
Data Index: 2530248 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19