Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3723 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3114. Min Range: -6.3114
Max Act: 6.3114. Min Act: -0.1700
Data Index: 4683043 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3114. Min Range: -6.3114
Max Act: 6.2489. Min Act: -0.1700
Data Index: 5069221 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3114. Min Range: -6.3114
Max Act: 6.2489. Min Act: -0.1700
Data Index: 282875 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3114. Min Range: -6.3114
Max Act: 6.1239. Min Act: -0.1700
Data Index: 8364059 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3114. Min Range: -6.3114
Max Act: 6.0614. Min Act: -0.1700
Data Index: 3610316 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3114. Min Range: -6.3114
Max Act: 6.0302. Min Act: -0.1700
Data Index: 6824221 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3114. Min Range: -6.3114
Max Act: 5.9989. Min Act: -0.1700
Data Index: 2790257 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3114. Min Range: -6.3114
Max Act: 6.0302. Min Act: -0.1700
Data Index: 5444056 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3114. Min Range: -6.3114
Max Act: 5.9989. Min Act: -0.1700
Data Index: 2244679 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3114. Min Range: -6.3114
Max Act: 5.9677. Min Act: -0.1700
Data Index: 2822462 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3114. Min Range: -6.3114
Max Act: 5.9364. Min Act: -0.1700
Data Index: 3429870 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3114. Min Range: -6.3114
Max Act: 5.9364. Min Act: -0.1700
Data Index: 1893780 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3114. Min Range: -6.3114
Max Act: 5.9052. Min Act: -0.1700
Data Index: 3678062 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3114. Min Range: -6.3114
Max Act: 5.8739. Min Act: -0.1700
Data Index: 2163581 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3114. Min Range: -6.3114
Max Act: 5.8739. Min Act: -0.1700
Data Index: 8520818 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3114. Min Range: -6.3114
Max Act: 5.8427. Min Act: -0.1700
Data Index: 2997344 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3114. Min Range: -6.3114
Max Act: 5.8114. Min Act: -0.1700
Data Index: 532386 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3114. Min Range: -6.3114
Max Act: 5.8114. Min Act: -0.1700
Data Index: 5722382 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3114. Min Range: -6.3114
Max Act: 5.7489. Min Act: -0.1700
Data Index: 5651004 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3114. Min Range: -6.3114
Max Act: 5.7489. Min Act: -0.1700
Data Index: 3553653 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #19