Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6251 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2431. Min Range: -3.2431
Max Act: 3.2431. Min Act: -0.1700
Data Index: 6223829 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2431. Min Range: -3.2431
Max Act: 3.0226. Min Act: -0.1700
Data Index: 5948115 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2431. Min Range: -3.2431
Max Act: 3.0226. Min Act: -0.1700
Data Index: 1119888 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2431. Min Range: -3.2431
Max Act: 2.9910. Min Act: -0.1700
Data Index: 7612277 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2431. Min Range: -3.2431
Max Act: 3.0068. Min Act: -0.1700
Data Index: 4213679 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2431. Min Range: -3.2431
Max Act: 2.9277. Min Act: -0.1700
Data Index: 4561800 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2431. Min Range: -3.2431
Max Act: 2.9436. Min Act: -0.1700
Data Index: 6327921 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2431. Min Range: -3.2431
Max Act: 2.9436. Min Act: -0.1700
Data Index: 6698086 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2431. Min Range: -3.2431
Max Act: 2.9436. Min Act: -0.1700
Data Index: 2380436 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2431. Min Range: -3.2431
Max Act: 2.9277. Min Act: -0.1700
Data Index: 2387195 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2431. Min Range: -3.2431
Max Act: 2.9277. Min Act: -0.1700
Data Index: 227507 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2431. Min Range: -3.2431
Max Act: 2.9277. Min Act: -0.1700
Data Index: 643250 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2431. Min Range: -3.2431
Max Act: 2.8960. Min Act: -0.1700
Data Index: 1395022 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2431. Min Range: -3.2431
Max Act: 2.8960. Min Act: -0.1700
Data Index: 595801 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2431. Min Range: -3.2431
Max Act: 2.8960. Min Act: -0.1700
Data Index: 4394004 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2431. Min Range: -3.2431
Max Act: 2.8960. Min Act: -0.1700
Data Index: 8097488 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2431. Min Range: -3.2431
Max Act: 2.9119. Min Act: -0.1700
Data Index: 5947041 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2431. Min Range: -3.2431
Max Act: 2.8960. Min Act: -0.1700
Data Index: 7743062 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2431. Min Range: -3.2431
Max Act: 2.8802. Min Act: -0.1700
Data Index: 646372 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2431. Min Range: -3.2431
Max Act: 2.8643. Min Act: -0.1700
Data Index: 8150985 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19