Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2446 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5849. Min Range: -4.5849
Max Act: 4.5849. Min Act: -0.1700
Data Index: 1340103 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5849. Min Range: -4.5849
Max Act: 4.4286. Min Act: -0.1700
Data Index: 998108 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5849. Min Range: -4.5849
Max Act: 4.4286. Min Act: -0.1700
Data Index: 676147 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5849. Min Range: -4.5849
Max Act: 4.3974. Min Act: -0.1700
Data Index: 1754811 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5849. Min Range: -4.5849
Max Act: 4.3974. Min Act: -0.1700
Data Index: 3545184 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5849. Min Range: -4.5849
Max Act: 4.3349. Min Act: -0.1700
Data Index: 476991 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5849. Min Range: -4.5849
Max Act: 4.3349. Min Act: -0.1700
Data Index: 2983975 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5849. Min Range: -4.5849
Max Act: 4.3661. Min Act: -0.1700
Data Index: 861725 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5849. Min Range: -4.5849
Max Act: 4.3349. Min Act: -0.1700
Data Index: 3838441 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5849. Min Range: -4.5849
Max Act: 4.3349. Min Act: -0.1700
Data Index: 4095396 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5849. Min Range: -4.5849
Max Act: 4.3349. Min Act: -0.1700
Data Index: 3205758 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5849. Min Range: -4.5849
Max Act: 4.3349. Min Act: -0.1700
Data Index: 7850690 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5849. Min Range: -4.5849
Max Act: 4.3036. Min Act: -0.1700
Data Index: 1773991 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5849. Min Range: -4.5849
Max Act: 4.3036. Min Act: -0.1700
Data Index: 2035657 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5849. Min Range: -4.5849
Max Act: 4.2724. Min Act: -0.1700
Data Index: 1074096 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5849. Min Range: -4.5849
Max Act: 4.2411. Min Act: -0.1700
Data Index: 7137778 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5849. Min Range: -4.5849
Max Act: 4.2411. Min Act: -0.1700
Data Index: 6800975 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5849. Min Range: -4.5849
Max Act: 4.2099. Min Act: -0.1700
Data Index: 3992793 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5849. Min Range: -4.5849
Max Act: 4.2411. Min Act: -0.1700
Data Index: 6008345 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5849. Min Range: -4.5849
Max Act: 4.1786. Min Act: -0.1700
Data Index: 5386855 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19