Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3366 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9763. Min Range: -5.9763
Max Act: 5.9763. Min Act: -0.1700
Data Index: 1527948 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9763. Min Range: -5.9763
Max Act: 5.8826. Min Act: -0.1700
Data Index: 550820 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9763. Min Range: -5.9763
Max Act: 5.8201. Min Act: -0.1700
Data Index: 1456795 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9763. Min Range: -5.9763
Max Act: 5.7263. Min Act: -0.1700
Data Index: 1374129 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9763. Min Range: -5.9763
Max Act: 5.6951. Min Act: -0.1700
Data Index: 6554807 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9763. Min Range: -5.9763
Max Act: 5.6326. Min Act: -0.1700
Data Index: 7851424 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9763. Min Range: -5.9763
Max Act: 5.5701. Min Act: -0.1700
Data Index: 2803433 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9763. Min Range: -5.9763
Max Act: 5.6013. Min Act: -0.1700
Data Index: 3776829 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9763. Min Range: -5.9763
Max Act: 5.6013. Min Act: -0.1700
Data Index: 1367476 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9763. Min Range: -5.9763
Max Act: 5.5388. Min Act: -0.1700
Data Index: 7827266 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9763. Min Range: -5.9763
Max Act: 5.5388. Min Act: -0.1700
Data Index: 8458721 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9763. Min Range: -5.9763
Max Act: 5.5388. Min Act: -0.1700
Data Index: 6860118 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9763. Min Range: -5.9763
Max Act: 5.4763. Min Act: -0.1700
Data Index: 7189294 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9763. Min Range: -5.9763
Max Act: 5.4138. Min Act: -0.1700
Data Index: 928445 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9763. Min Range: -5.9763
Max Act: 5.3201. Min Act: -0.1700
Data Index: 7490401 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9763. Min Range: -5.9763
Max Act: 5.3201. Min Act: -0.1700
Data Index: 4157445 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9763. Min Range: -5.9763
Max Act: 5.3201. Min Act: -0.1700
Data Index: 4878976 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9763. Min Range: -5.9763
Max Act: 5.2888. Min Act: -0.1700
Data Index: 4229051 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9763. Min Range: -5.9763
Max Act: 5.2888. Min Act: -0.1700
Data Index: 4804799 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9763. Min Range: -5.9763
Max Act: 5.2576. Min Act: -0.1700
Data Index: 1395057 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19