Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2412 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6434. Min Range: -8.6434
Max Act: 8.6434. Min Act: -0.1700
Data Index: 6047661 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6434. Min Range: -8.6434
Max Act: 7.9872. Min Act: -0.1700
Data Index: 5513298 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6434. Min Range: -8.6434
Max Act: 7.9559. Min Act: -0.1700
Data Index: 6095518 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6434. Min Range: -8.6434
Max Act: 7.9247. Min Act: -0.1700
Data Index: 1970348 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6434. Min Range: -8.6434
Max Act: 7.8934. Min Act: -0.1700
Data Index: 4505249 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6434. Min Range: -8.6434
Max Act: 7.7684. Min Act: -0.1700
Data Index: 7289324 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6434. Min Range: -8.6434
Max Act: 7.7372. Min Act: -0.1700
Data Index: 5022269 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6434. Min Range: -8.6434
Max Act: 7.7059. Min Act: -0.1700
Data Index: 969949 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6434. Min Range: -8.6434
Max Act: 7.7059. Min Act: -0.1700
Data Index: 1162375 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6434. Min Range: -8.6434
Max Act: 7.6122. Min Act: -0.1700
Data Index: 5062687 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6434. Min Range: -8.6434
Max Act: 7.6122. Min Act: -0.1700
Data Index: 18557 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6434. Min Range: -8.6434
Max Act: 7.6122. Min Act: -0.1700
Data Index: 5690719 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6434. Min Range: -8.6434
Max Act: 7.5809. Min Act: -0.1700
Data Index: 5084440 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6434. Min Range: -8.6434
Max Act: 7.5809. Min Act: -0.1700
Data Index: 2574007 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6434. Min Range: -8.6434
Max Act: 7.5809. Min Act: -0.1700
Data Index: 8496007 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6434. Min Range: -8.6434
Max Act: 7.5184. Min Act: -0.1700
Data Index: 3213420 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6434. Min Range: -8.6434
Max Act: 7.5184. Min Act: -0.1700
Data Index: 2568339 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6434. Min Range: -8.6434
Max Act: 7.5497. Min Act: -0.1700
Data Index: 2910226 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6434. Min Range: -8.6434
Max Act: 7.5184. Min Act: -0.1700
Data Index: 3277835 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6434. Min Range: -8.6434
Max Act: 7.4872. Min Act: -0.1700
Data Index: 8509754 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19