Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2012 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.8089. Min Act: -0.1700
Data Index: 2815465 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.7151. Min Act: -0.1700
Data Index: 7790208 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.6214. Min Act: -0.1700
Data Index: 1524201 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.4964. Min Act: -0.1700
Data Index: 5042732 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.4964. Min Act: -0.1700
Data Index: 2212661 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.4339. Min Act: -0.1700
Data Index: 2911020 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.4026. Min Act: -0.1700
Data Index: 2034603 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.3401. Min Act: -0.1700
Data Index: 7500414 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.3401. Min Act: -0.1700
Data Index: 637729 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.2776. Min Act: -0.1700
Data Index: 6677925 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.2776. Min Act: -0.1700
Data Index: 8256078 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.2776. Min Act: -0.1700
Data Index: 4079787 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.2776. Min Act: -0.1700
Data Index: 2460067 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.2776. Min Act: -0.1700
Data Index: 5226200 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.2464. Min Act: -0.1700
Data Index: 6818694 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.2464. Min Act: -0.1700
Data Index: 5369962 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.2464. Min Act: -0.1700
Data Index: 3670173 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.2464. Min Act: -0.1700
Data Index: 897898 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.2464. Min Act: -0.1700
Data Index: 6726507 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.2464. Min Act: -0.1700
Data Index: 2574810 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #19