Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1492 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3871. Min Range: -5.3871
Max Act: 5.3871. Min Act: -0.1700
Data Index: 3185403 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3871. Min Range: -5.3871
Max Act: 5.1683. Min Act: -0.1700
Data Index: 5799993 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3871. Min Range: -5.3871
Max Act: 5.0746. Min Act: -0.1700
Data Index: 6575933 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3871. Min Range: -5.3871
Max Act: 5.0433. Min Act: -0.1700
Data Index: 7212497 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.9808. Min Act: -0.1700
Data Index: 4668592 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.9808. Min Act: -0.1700
Data Index: 3949700 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.9808. Min Act: -0.1700
Data Index: 623 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.9183. Min Act: -0.1700
Data Index: 8094345 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.8558. Min Act: -0.1700
Data Index: 4188612 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.8871. Min Act: -0.1700
Data Index: 4074990 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.8558. Min Act: -0.1700
Data Index: 4575378 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.8558. Min Act: -0.1700
Data Index: 5187906 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.8246. Min Act: -0.1700
Data Index: 8175658 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.7933. Min Act: -0.1700
Data Index: 2466228 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.8246. Min Act: -0.1700
Data Index: 7927177 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.7933. Min Act: -0.1700
Data Index: 5374677 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.7933. Min Act: -0.1700
Data Index: 4236946 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.7933. Min Act: -0.1700
Data Index: 5549420 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.7933. Min Act: -0.1700
Data Index: 6246149 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.7621. Min Act: -0.1700
Data Index: 5009893 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19