Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3421 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2724. Min Range: -7.2724
Max Act: 7.2724. Min Act: -0.1700
Data Index: 7382753 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2724. Min Range: -7.2724
Max Act: 7.2412. Min Act: -0.1700
Data Index: 6638674 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2724. Min Range: -7.2724
Max Act: 7.0224. Min Act: -0.1700
Data Index: 1142483 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2724. Min Range: -7.2724
Max Act: 6.9287. Min Act: -0.1700
Data Index: 4055502 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2724. Min Range: -7.2724
Max Act: 6.8974. Min Act: -0.1700
Data Index: 501594 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2724. Min Range: -7.2724
Max Act: 6.8349. Min Act: -0.1700
Data Index: 7090614 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2724. Min Range: -7.2724
Max Act: 6.8037. Min Act: -0.1700
Data Index: 1829249 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2724. Min Range: -7.2724
Max Act: 6.7724. Min Act: -0.1700
Data Index: 7670787 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2724. Min Range: -7.2724
Max Act: 6.7724. Min Act: -0.1700
Data Index: 4719268 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2724. Min Range: -7.2724
Max Act: 6.7099. Min Act: -0.1700
Data Index: 7708405 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2724. Min Range: -7.2724
Max Act: 6.7099. Min Act: -0.1700
Data Index: 7702431 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2724. Min Range: -7.2724
Max Act: 6.6787. Min Act: -0.1700
Data Index: 6218826 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2724. Min Range: -7.2724
Max Act: 6.6787. Min Act: -0.1700
Data Index: 8536720 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2724. Min Range: -7.2724
Max Act: 6.6787. Min Act: -0.1700
Data Index: 669869 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2724. Min Range: -7.2724
Max Act: 6.6787. Min Act: -0.1700
Data Index: 5162299 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2724. Min Range: -7.2724
Max Act: 6.6474. Min Act: -0.1700
Data Index: 2566660 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2724. Min Range: -7.2724
Max Act: 6.6162. Min Act: -0.1700
Data Index: 4704079 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2724. Min Range: -7.2724
Max Act: 6.6474. Min Act: -0.1700
Data Index: 3197085 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2724. Min Range: -7.2724
Max Act: 6.6162. Min Act: -0.1700
Data Index: 7779681 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2724. Min Range: -7.2724
Max Act: 6.5849. Min Act: -0.1700
Data Index: 1997371 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19