Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4243 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4590. Min Range: -7.4590
Max Act: 7.4590. Min Act: -0.1700
Data Index: 2547943 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4590. Min Range: -7.4590
Max Act: 7.4590. Min Act: -0.1700
Data Index: 522617 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4590. Min Range: -7.4590
Max Act: 7.1778. Min Act: -0.1700
Data Index: 6239978 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4590. Min Range: -7.4590
Max Act: 7.0840. Min Act: -0.1700
Data Index: 6782361 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4590. Min Range: -7.4590
Max Act: 7.0528. Min Act: -0.1700
Data Index: 6494359 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4590. Min Range: -7.4590
Max Act: 7.0215. Min Act: -0.1700
Data Index: 7181932 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4590. Min Range: -7.4590
Max Act: 7.0215. Min Act: -0.1700
Data Index: 5077610 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4590. Min Range: -7.4590
Max Act: 7.0215. Min Act: -0.1700
Data Index: 7887256 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4590. Min Range: -7.4590
Max Act: 6.9590. Min Act: -0.1700
Data Index: 4067545 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4590. Min Range: -7.4590
Max Act: 6.9590. Min Act: -0.1700
Data Index: 6454164 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4590. Min Range: -7.4590
Max Act: 6.9278. Min Act: -0.1700
Data Index: 615680 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4590. Min Range: -7.4590
Max Act: 6.8340. Min Act: -0.1700
Data Index: 8483291 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4590. Min Range: -7.4590
Max Act: 6.8028. Min Act: -0.1700
Data Index: 2182935 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4590. Min Range: -7.4590
Max Act: 6.8028. Min Act: -0.1700
Data Index: 3982260 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4590. Min Range: -7.4590
Max Act: 6.8028. Min Act: -0.1700
Data Index: 5799345 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4590. Min Range: -7.4590
Max Act: 6.7090. Min Act: -0.1700
Data Index: 8023650 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4590. Min Range: -7.4590
Max Act: 6.7403. Min Act: -0.1700
Data Index: 2319993 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4590. Min Range: -7.4590
Max Act: 6.7403. Min Act: -0.1700
Data Index: 380322 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4590. Min Range: -7.4590
Max Act: 6.7403. Min Act: -0.1700
Data Index: 4998525 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4590. Min Range: -7.4590
Max Act: 6.7090. Min Act: -0.1700
Data Index: 1725743 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19