Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3521 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2883. Min Range: -5.2883
Max Act: 5.2883. Min Act: -0.1700
Data Index: 5230592 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2883. Min Range: -5.2883
Max Act: 5.1945. Min Act: -0.1700
Data Index: 8174550 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2883. Min Range: -5.2883
Max Act: 5.1633. Min Act: -0.1700
Data Index: 898755 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2883. Min Range: -5.2883
Max Act: 4.9445. Min Act: -0.1700
Data Index: 8497312 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2883. Min Range: -5.2883
Max Act: 4.9445. Min Act: -0.1700
Data Index: 2187593 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2883. Min Range: -5.2883
Max Act: 4.8820. Min Act: -0.1700
Data Index: 5728368 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2883. Min Range: -5.2883
Max Act: 4.8820. Min Act: -0.1700
Data Index: 8021191 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2883. Min Range: -5.2883
Max Act: 4.8820. Min Act: -0.1700
Data Index: 3901156 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2883. Min Range: -5.2883
Max Act: 4.8820. Min Act: -0.1700
Data Index: 2114931 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2883. Min Range: -5.2883
Max Act: 4.8508. Min Act: -0.1700
Data Index: 1163061 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2883. Min Range: -5.2883
Max Act: 4.8195. Min Act: -0.1700
Data Index: 2823459 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2883. Min Range: -5.2883
Max Act: 4.8508. Min Act: -0.1700
Data Index: 5403924 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2883. Min Range: -5.2883
Max Act: 4.8195. Min Act: -0.1700
Data Index: 4580696 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2883. Min Range: -5.2883
Max Act: 4.7883. Min Act: -0.1700
Data Index: 6782388 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2883. Min Range: -5.2883
Max Act: 4.8195. Min Act: -0.1700
Data Index: 6116769 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2883. Min Range: -5.2883
Max Act: 4.7570. Min Act: -0.1700
Data Index: 7905954 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2883. Min Range: -5.2883
Max Act: 4.7883. Min Act: -0.1700
Data Index: 6750920 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2883. Min Range: -5.2883
Max Act: 4.7883. Min Act: -0.1700
Data Index: 5446632 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2883. Min Range: -5.2883
Max Act: 4.7883. Min Act: -0.1700
Data Index: 4772696 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2883. Min Range: -5.2883
Max Act: 4.7883. Min Act: -0.1700
Data Index: 2570613 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #19