Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3240 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2731. Min Range: -3.2731
Max Act: 3.2731. Min Act: -0.1700
Data Index: 8094399 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2731. Min Range: -3.2731
Max Act: 3.1788. Min Act: -0.1700
Data Index: 6320995 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2731. Min Range: -3.2731
Max Act: 3.1631. Min Act: -0.1700
Data Index: 3543008 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2731. Min Range: -3.2731
Max Act: 3.1473. Min Act: -0.1700
Data Index: 1911385 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2731. Min Range: -3.2731
Max Act: 3.1316. Min Act: -0.1700
Data Index: 752258 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2731. Min Range: -3.2731
Max Act: 3.1158. Min Act: -0.1700
Data Index: 7472190 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2731. Min Range: -3.2731
Max Act: 3.1001. Min Act: -0.1700
Data Index: 3126756 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2731. Min Range: -3.2731
Max Act: 3.0843. Min Act: -0.1700
Data Index: 1911386 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2731. Min Range: -3.2731
Max Act: 3.0685. Min Act: -0.1700
Data Index: 1911387 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2731. Min Range: -3.2731
Max Act: 3.0685. Min Act: -0.1700
Data Index: 6603614 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2731. Min Range: -3.2731
Max Act: 3.0212. Min Act: -0.1700
Data Index: 1911388 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2731. Min Range: -3.2731
Max Act: 3.0212. Min Act: -0.1700
Data Index: 7238229 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2731. Min Range: -3.2731
Max Act: 3.0212. Min Act: -0.1700
Data Index: 3809471 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2731. Min Range: -3.2731
Max Act: 3.0054. Min Act: -0.1700
Data Index: 807128 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2731. Min Range: -3.2731
Max Act: 3.0054. Min Act: -0.1700
Data Index: 6675388 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2731. Min Range: -3.2731
Max Act: 3.0054. Min Act: -0.1700
Data Index: 866025 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2731. Min Range: -3.2731
Max Act: 3.0054. Min Act: -0.1700
Data Index: 1911393 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2731. Min Range: -3.2731
Max Act: 3.0054. Min Act: -0.1700
Data Index: 866031 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2731. Min Range: -3.2731
Max Act: 3.0054. Min Act: -0.1700
Data Index: 2730275 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2731. Min Range: -3.2731
Max Act: 2.9896. Min Act: -0.1700
Data Index: 6942358 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19