Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3938 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2801. Min Range: -5.2801
Max Act: 5.2801. Min Act: -0.1700
Data Index: 7398072 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2801. Min Range: -5.2801
Max Act: 5.0926. Min Act: -0.1700
Data Index: 4057847 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2801. Min Range: -5.2801
Max Act: 5.0926. Min Act: -0.1700
Data Index: 1947242 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2801. Min Range: -5.2801
Max Act: 5.0614. Min Act: -0.1700
Data Index: 561236 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2801. Min Range: -5.2801
Max Act: 4.9989. Min Act: -0.1700
Data Index: 347077 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2801. Min Range: -5.2801
Max Act: 4.9676. Min Act: -0.1700
Data Index: 3731759 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2801. Min Range: -5.2801
Max Act: 4.9364. Min Act: -0.1700
Data Index: 6726132 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2801. Min Range: -5.2801
Max Act: 4.9676. Min Act: -0.1700
Data Index: 3764397 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2801. Min Range: -5.2801
Max Act: 4.9676. Min Act: -0.1700
Data Index: 5606508 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2801. Min Range: -5.2801
Max Act: 4.9676. Min Act: -0.1700
Data Index: 8027598 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2801. Min Range: -5.2801
Max Act: 4.9989. Min Act: -0.1700
Data Index: 5402107 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2801. Min Range: -5.2801
Max Act: 4.9676. Min Act: -0.1700
Data Index: 5475183 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2801. Min Range: -5.2801
Max Act: 4.9676. Min Act: -0.1700
Data Index: 2524067 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2801. Min Range: -5.2801
Max Act: 4.9051. Min Act: -0.1700
Data Index: 5546791 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2801. Min Range: -5.2801
Max Act: 4.9364. Min Act: -0.1700
Data Index: 3655803 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2801. Min Range: -5.2801
Max Act: 4.9364. Min Act: -0.1700
Data Index: 6185035 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2801. Min Range: -5.2801
Max Act: 4.9364. Min Act: -0.1700
Data Index: 781181 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2801. Min Range: -5.2801
Max Act: 4.9364. Min Act: -0.1700
Data Index: 2158000 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2801. Min Range: -5.2801
Max Act: 4.9364. Min Act: -0.1700
Data Index: 3314766 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2801. Min Range: -5.2801
Max Act: 4.9364. Min Act: -0.1700
Data Index: 5416055 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #19