Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3432 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8716. Min Range: -2.8716
Max Act: 2.8716. Min Act: -0.1700
Data Index: 247443 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8716. Min Range: -2.8716
Max Act: 2.8557. Min Act: -0.1700
Data Index: 4124384 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8716. Min Range: -2.8716
Max Act: 2.8399. Min Act: -0.1700
Data Index: 395575 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8716. Min Range: -2.8716
Max Act: 2.8399. Min Act: -0.1700
Data Index: 4141190 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8716. Min Range: -2.8716
Max Act: 2.8240. Min Act: -0.1700
Data Index: 7652849 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8716. Min Range: -2.8716
Max Act: 2.8240. Min Act: -0.1700
Data Index: 6546477 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8716. Min Range: -2.8716
Max Act: 2.8080. Min Act: -0.1700
Data Index: 3620148 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8716. Min Range: -2.8716
Max Act: 2.8080. Min Act: -0.1700
Data Index: 5210223 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8716. Min Range: -2.8716
Max Act: 2.8080. Min Act: -0.1700
Data Index: 6096339 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8716. Min Range: -2.8716
Max Act: 2.8240. Min Act: -0.1700
Data Index: 8283635 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8716. Min Range: -2.8716
Max Act: 2.7921. Min Act: -0.1700
Data Index: 2943293 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8716. Min Range: -2.8716
Max Act: 2.7921. Min Act: -0.1700
Data Index: 3775833 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8716. Min Range: -2.8716
Max Act: 2.7921. Min Act: -0.1700
Data Index: 8426431 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8716. Min Range: -2.8716
Max Act: 2.7762. Min Act: -0.1700
Data Index: 5272265 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8716. Min Range: -2.8716
Max Act: 2.7602. Min Act: -0.1700
Data Index: 8115236 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8716. Min Range: -2.8716
Max Act: 2.7602. Min Act: -0.1700
Data Index: 1959619 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8716. Min Range: -2.8716
Max Act: 2.7602. Min Act: -0.1700
Data Index: 4978092 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8716. Min Range: -2.8716
Max Act: 2.7602. Min Act: -0.1700
Data Index: 6166559 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8716. Min Range: -2.8716
Max Act: 2.7602. Min Act: -0.1700
Data Index: 4879353 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8716. Min Range: -2.8716
Max Act: 2.7283. Min Act: -0.1700
Data Index: 1959621 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19