Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6220 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5652. Min Range: -6.5652
Max Act: 6.5652. Min Act: -0.1700
Data Index: 1088947 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5652. Min Range: -6.5652
Max Act: 6.5652. Min Act: -0.1700
Data Index: 1916600 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5652. Min Range: -6.5652
Max Act: 6.5652. Min Act: -0.1700
Data Index: 8506012 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5652. Min Range: -6.5652
Max Act: 6.5340. Min Act: -0.1699
Data Index: 4570187 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5652. Min Range: -6.5652
Max Act: 6.5340. Min Act: -0.1700
Data Index: 3748049 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5652. Min Range: -6.5652
Max Act: 6.5340. Min Act: -0.1700
Data Index: 732913 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5652. Min Range: -6.5652
Max Act: 6.5340. Min Act: -0.1700
Data Index: 7627106 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5652. Min Range: -6.5652
Max Act: 6.4715. Min Act: -0.1700
Data Index: 5115400 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5652. Min Range: -6.5652
Max Act: 6.4715. Min Act: -0.1698
Data Index: 3516484 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5652. Min Range: -6.5652
Max Act: 6.4402. Min Act: -0.1700
Data Index: 372005 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5652. Min Range: -6.5652
Max Act: 6.4402. Min Act: -0.1700
Data Index: 6922206 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5652. Min Range: -6.5652
Max Act: 6.4090. Min Act: -0.1700
Data Index: 8656379 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5652. Min Range: -6.5652
Max Act: 6.4090. Min Act: -0.1700
Data Index: 3211315 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5652. Min Range: -6.5652
Max Act: 6.3777. Min Act: -0.1700
Data Index: 2776889 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5652. Min Range: -6.5652
Max Act: 6.3777. Min Act: -0.1700
Data Index: 2549415 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5652. Min Range: -6.5652
Max Act: 6.3777. Min Act: -0.1700
Data Index: 7218733 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5652. Min Range: -6.5652
Max Act: 6.3152. Min Act: -0.1700
Data Index: 860387 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5652. Min Range: -6.5652
Max Act: 6.3465. Min Act: -0.1700
Data Index: 196332 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5652. Min Range: -6.5652
Max Act: 6.3777. Min Act: -0.1700
Data Index: 8173975 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5652. Min Range: -6.5652
Max Act: 6.3152. Min Act: -0.1700
Data Index: 6102880 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19