Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2780 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9262. Min Range: -8.9262
Max Act: 8.9262. Min Act: -0.1700
Data Index: 686652 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9262. Min Range: -8.9262
Max Act: 8.5512. Min Act: -0.1700
Data Index: 6609980 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9262. Min Range: -8.9262
Max Act: 8.4887. Min Act: -0.1700
Data Index: 616914 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9262. Min Range: -8.9262
Max Act: 8.3637. Min Act: -0.1700
Data Index: 3776378 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9262. Min Range: -8.9262
Max Act: 8.1762. Min Act: -0.1700
Data Index: 5874653 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9262. Min Range: -8.9262
Max Act: 8.1137. Min Act: -0.1700
Data Index: 1419302 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9262. Min Range: -8.9262
Max Act: 8.1137. Min Act: -0.1700
Data Index: 615801 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9262. Min Range: -8.9262
Max Act: 7.9262. Min Act: -0.1700
Data Index: 8289070 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9262. Min Range: -8.9262
Max Act: 7.8637. Min Act: -0.1700
Data Index: 3894360 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9262. Min Range: -8.9262
Max Act: 7.8637. Min Act: -0.1700
Data Index: 928197 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9262. Min Range: -8.9262
Max Act: 7.8637. Min Act: -0.1700
Data Index: 8596529 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9262. Min Range: -8.9262
Max Act: 7.8637. Min Act: -0.1700
Data Index: 8028738 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9262. Min Range: -8.9262
Max Act: 7.9262. Min Act: -0.1700
Data Index: 6963334 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9262. Min Range: -8.9262
Max Act: 7.8637. Min Act: -0.1700
Data Index: 4110268 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9262. Min Range: -8.9262
Max Act: 7.8637. Min Act: -0.1700
Data Index: 1093439 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9262. Min Range: -8.9262
Max Act: 7.8012. Min Act: -0.1700
Data Index: 1688091 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9262. Min Range: -8.9262
Max Act: 7.8012. Min Act: -0.1700
Data Index: 117115 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9262. Min Range: -8.9262
Max Act: 7.8012. Min Act: -0.1700
Data Index: 3334980 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9262. Min Range: -8.9262
Max Act: 7.7387. Min Act: -0.1700
Data Index: 6578954 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9262. Min Range: -8.9262
Max Act: 7.7387. Min Act: -0.1700
Data Index: 1084309 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #19