Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 515 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6516. Min Range: -7.6516
Max Act: 7.6516. Min Act: -0.1700
Data Index: 61678 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6516. Min Range: -7.6516
Max Act: 7.4329. Min Act: -0.1700
Data Index: 5788561 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6516. Min Range: -7.6516
Max Act: 7.4641. Min Act: -0.1700
Data Index: 8129613 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6516. Min Range: -7.6516
Max Act: 7.4016. Min Act: -0.1700
Data Index: 7069488 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6516. Min Range: -7.6516
Max Act: 7.4016. Min Act: -0.1700
Data Index: 2123281 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6516. Min Range: -7.6516
Max Act: 7.3391. Min Act: -0.1700
Data Index: 2588593 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6516. Min Range: -7.6516
Max Act: 7.2141. Min Act: -0.1700
Data Index: 8806566 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6516. Min Range: -7.6516
Max Act: 7.1829. Min Act: -0.1700
Data Index: 4496610 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6516. Min Range: -7.6516
Max Act: 7.2141. Min Act: -0.1700
Data Index: 7581370 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6516. Min Range: -7.6516
Max Act: 7.1829. Min Act: -0.1700
Data Index: 2726651 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6516. Min Range: -7.6516
Max Act: 7.1829. Min Act: -0.1700
Data Index: 3799241 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6516. Min Range: -7.6516
Max Act: 7.1516. Min Act: -0.1700
Data Index: 4845250 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6516. Min Range: -7.6516
Max Act: 7.1516. Min Act: -0.1700
Data Index: 5328430 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6516. Min Range: -7.6516
Max Act: 7.1204. Min Act: -0.1700
Data Index: 2431309 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6516. Min Range: -7.6516
Max Act: 7.1516. Min Act: -0.1700
Data Index: 5858770 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6516. Min Range: -7.6516
Max Act: 7.1204. Min Act: -0.1700
Data Index: 1059003 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6516. Min Range: -7.6516
Max Act: 7.1204. Min Act: -0.1700
Data Index: 5245458 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6516. Min Range: -7.6516
Max Act: 7.1204. Min Act: -0.1700
Data Index: 7085171 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6516. Min Range: -7.6516
Max Act: 7.1204. Min Act: -0.1700
Data Index: 7315633 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6516. Min Range: -7.6516
Max Act: 7.1204. Min Act: -0.1700
Data Index: 5301498 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19