Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3081 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8836. Min Range: -6.8836
Max Act: 6.8836. Min Act: -0.1700
Data Index: 5036634 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8836. Min Range: -6.8836
Max Act: 6.7899. Min Act: -0.1700
Data Index: 1079452 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8836. Min Range: -6.8836
Max Act: 6.7586. Min Act: -0.1700
Data Index: 8008199 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8836. Min Range: -6.8836
Max Act: 6.6961. Min Act: -0.1700
Data Index: 7787221 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8836. Min Range: -6.8836
Max Act: 6.6649. Min Act: -0.1700
Data Index: 5106361 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8836. Min Range: -6.8836
Max Act: 6.6336. Min Act: -0.1700
Data Index: 6455292 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8836. Min Range: -6.8836
Max Act: 6.6649. Min Act: -0.1700
Data Index: 2565507 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8836. Min Range: -6.8836
Max Act: 6.6649. Min Act: -0.1700
Data Index: 7065538 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8836. Min Range: -6.8836
Max Act: 6.5399. Min Act: -0.1700
Data Index: 6938035 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8836. Min Range: -6.8836
Max Act: 6.5711. Min Act: -0.1700
Data Index: 5533893 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8836. Min Range: -6.8836
Max Act: 6.5711. Min Act: -0.1700
Data Index: 7072942 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8836. Min Range: -6.8836
Max Act: 6.5399. Min Act: -0.1700
Data Index: 3083593 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8836. Min Range: -6.8836
Max Act: 6.4774. Min Act: -0.1700
Data Index: 1803140 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8836. Min Range: -6.8836
Max Act: 6.4774. Min Act: -0.1700
Data Index: 2402862 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8836. Min Range: -6.8836
Max Act: 6.4774. Min Act: -0.1700
Data Index: 4906020 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8836. Min Range: -6.8836
Max Act: 6.4461. Min Act: -0.1700
Data Index: 3569934 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8836. Min Range: -6.8836
Max Act: 6.4461. Min Act: -0.1700
Data Index: 6103299 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8836. Min Range: -6.8836
Max Act: 6.4461. Min Act: -0.1700
Data Index: 7961943 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8836. Min Range: -6.8836
Max Act: 6.4461. Min Act: -0.1700
Data Index: 6071483 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8836. Min Range: -6.8836
Max Act: 6.4461. Min Act: -0.1700
Data Index: 3515272 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19