Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3247 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6453. Min Range: -4.6453
Max Act: 4.6453. Min Act: -0.1700
Data Index: 2594056 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6453. Min Range: -4.6453
Max Act: 4.5203. Min Act: -0.1700
Data Index: 8260973 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6453. Min Range: -4.6453
Max Act: 4.5203. Min Act: -0.1700
Data Index: 4142353 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6453. Min Range: -4.6453
Max Act: 4.4891. Min Act: -0.1700
Data Index: 4555243 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6453. Min Range: -4.6453
Max Act: 4.4266. Min Act: -0.1700
Data Index: 8325203 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6453. Min Range: -4.6453
Max Act: 4.3641. Min Act: -0.1700
Data Index: 98720 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6453. Min Range: -4.6453
Max Act: 4.3641. Min Act: -0.1700
Data Index: 6527122 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6453. Min Range: -4.6453
Max Act: 4.3641. Min Act: -0.1700
Data Index: 3619060 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6453. Min Range: -4.6453
Max Act: 4.3641. Min Act: -0.1700
Data Index: 1684795 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6453. Min Range: -4.6453
Max Act: 4.3328. Min Act: -0.1700
Data Index: 2349781 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6453. Min Range: -4.6453
Max Act: 4.3328. Min Act: -0.1700
Data Index: 8741287 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6453. Min Range: -4.6453
Max Act: 4.3328. Min Act: -0.1700
Data Index: 414423 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6453. Min Range: -4.6453
Max Act: 4.3328. Min Act: -0.1700
Data Index: 1486272 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6453. Min Range: -4.6453
Max Act: 4.3016. Min Act: -0.1700
Data Index: 3334788 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6453. Min Range: -4.6453
Max Act: 4.3016. Min Act: -0.1700
Data Index: 1756075 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6453. Min Range: -4.6453
Max Act: 4.3016. Min Act: -0.1700
Data Index: 307462 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6453. Min Range: -4.6453
Max Act: 4.3016. Min Act: -0.1700
Data Index: 4603110 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6453. Min Range: -4.6453
Max Act: 4.3016. Min Act: -0.1700
Data Index: 2429116 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6453. Min Range: -4.6453
Max Act: 4.2390. Min Act: -0.1700
Data Index: 3063408 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6453. Min Range: -4.6453
Max Act: 4.3016. Min Act: -0.1700
Data Index: 3115768 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19