Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3129 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9701. Min Range: -2.9701
Max Act: 2.9701. Min Act: -0.1700
Data Index: 5242510 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9701. Min Range: -2.9701
Max Act: 2.9384. Min Act: -0.1700
Data Index: 6140444 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9701. Min Range: -2.9701
Max Act: 2.9226. Min Act: -0.1700
Data Index: 2029465 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9701. Min Range: -2.9701
Max Act: 2.9067. Min Act: -0.1700
Data Index: 4145400 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9701. Min Range: -2.9701
Max Act: 2.9067. Min Act: -0.1700
Data Index: 5579955 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9701. Min Range: -2.9701
Max Act: 2.8909. Min Act: -0.1700
Data Index: 559067 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9701. Min Range: -2.9701
Max Act: 2.8909. Min Act: -0.1700
Data Index: 6245960 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9701. Min Range: -2.9701
Max Act: 2.8909. Min Act: -0.1700
Data Index: 5991735 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9701. Min Range: -2.9701
Max Act: 2.8909. Min Act: -0.1700
Data Index: 8232186 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9701. Min Range: -2.9701
Max Act: 2.8909. Min Act: -0.1700
Data Index: 8190103 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9701. Min Range: -2.9701
Max Act: 2.8750. Min Act: -0.1700
Data Index: 937337 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9701. Min Range: -2.9701
Max Act: 2.8591. Min Act: -0.1700
Data Index: 2270814 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9701. Min Range: -2.9701
Max Act: 2.8432. Min Act: -0.1700
Data Index: 8074446 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9701. Min Range: -2.9701
Max Act: 2.8432. Min Act: -0.1700
Data Index: 3532040 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9701. Min Range: -2.9701
Max Act: 2.8432. Min Act: -0.1700
Data Index: 1855046 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9701. Min Range: -2.9701
Max Act: 2.8432. Min Act: -0.1700
Data Index: 1458269 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9701. Min Range: -2.9701
Max Act: 2.8432. Min Act: -0.1700
Data Index: 7048052 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9701. Min Range: -2.9701
Max Act: 2.8273. Min Act: -0.1700
Data Index: 5437041 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9701. Min Range: -2.9701
Max Act: 2.8273. Min Act: -0.1700
Data Index: 5991709 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9701. Min Range: -2.9701
Max Act: 2.8273. Min Act: -0.1700
Data Index: 3038680 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19