Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 528 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6953. Min Range: -5.6953
Max Act: 5.6953. Min Act: -0.1700
Data Index: 7592340 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6953. Min Range: -5.6953
Max Act: 5.4766. Min Act: -0.1700
Data Index: 6448165 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6953. Min Range: -5.6953
Max Act: 5.4141. Min Act: -0.1700
Data Index: 2034940 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6953. Min Range: -5.6953
Max Act: 5.3203. Min Act: -0.1700
Data Index: 4202422 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6953. Min Range: -5.6953
Max Act: 5.2891. Min Act: -0.1700
Data Index: 1730730 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6953. Min Range: -5.6953
Max Act: 5.2578. Min Act: -0.1700
Data Index: 7244226 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6953. Min Range: -5.6953
Max Act: 5.2578. Min Act: -0.1700
Data Index: 5081901 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6953. Min Range: -5.6953
Max Act: 5.2266. Min Act: -0.1700
Data Index: 793061 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6953. Min Range: -5.6953
Max Act: 5.2266. Min Act: -0.1700
Data Index: 5463281 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6953. Min Range: -5.6953
Max Act: 5.2266. Min Act: -0.1700
Data Index: 1577942 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6953. Min Range: -5.6953
Max Act: 5.2266. Min Act: -0.1700
Data Index: 6809798 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6953. Min Range: -5.6953
Max Act: 5.2266. Min Act: -0.1700
Data Index: 6520937 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6953. Min Range: -5.6953
Max Act: 5.1641. Min Act: -0.1700
Data Index: 1471812 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6953. Min Range: -5.6953
Max Act: 5.1953. Min Act: -0.1700
Data Index: 6808948 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6953. Min Range: -5.6953
Max Act: 5.1953. Min Act: -0.1700
Data Index: 1524546 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6953. Min Range: -5.6953
Max Act: 5.1328. Min Act: -0.1700
Data Index: 7472723 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6953. Min Range: -5.6953
Max Act: 5.1641. Min Act: -0.1700
Data Index: 1603604 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6953. Min Range: -5.6953
Max Act: 5.1641. Min Act: -0.1700
Data Index: 7369928 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6953. Min Range: -5.6953
Max Act: 5.1328. Min Act: -0.1700
Data Index: 1813401 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6953. Min Range: -5.6953
Max Act: 5.1641. Min Act: -0.1700
Data Index: 2788844 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19