Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3083 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2742. Min Range: -3.2742
Max Act: 3.2742. Min Act: -0.1700
Data Index: 718515 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2742. Min Range: -3.2742
Max Act: 3.2742. Min Act: -0.1700
Data Index: 4694050 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2742. Min Range: -3.2742
Max Act: 3.2270. Min Act: -0.1700
Data Index: 7761329 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2742. Min Range: -3.2742
Max Act: 3.2113. Min Act: -0.1700
Data Index: 7386109 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2742. Min Range: -3.2742
Max Act: 3.2270. Min Act: -0.1700
Data Index: 920607 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2742. Min Range: -3.2742
Max Act: 3.1956. Min Act: -0.1700
Data Index: 8682918 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2742. Min Range: -3.2742
Max Act: 3.1799. Min Act: -0.1700
Data Index: 3544676 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2742. Min Range: -3.2742
Max Act: 3.1641. Min Act: -0.1700
Data Index: 4344115 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2742. Min Range: -3.2742
Max Act: 3.1641. Min Act: -0.1700
Data Index: 3355998 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2742. Min Range: -3.2742
Max Act: 3.1169. Min Act: -0.1700
Data Index: 2725772 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2742. Min Range: -3.2742
Max Act: 3.1326. Min Act: -0.1700
Data Index: 5695166 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2742. Min Range: -3.2742
Max Act: 3.1484. Min Act: -0.1700
Data Index: 7761334 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2742. Min Range: -3.2742
Max Act: 3.1011. Min Act: -0.1700
Data Index: 5004268 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2742. Min Range: -3.2742
Max Act: 3.0854. Min Act: -0.1700
Data Index: 8647202 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2742. Min Range: -3.2742
Max Act: 3.0854. Min Act: -0.1700
Data Index: 5695163 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2742. Min Range: -3.2742
Max Act: 3.1169. Min Act: -0.1700
Data Index: 630690 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2742. Min Range: -3.2742
Max Act: 3.1011. Min Act: -0.1700
Data Index: 5136892 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2742. Min Range: -3.2742
Max Act: 3.0696. Min Act: -0.1700
Data Index: 3355993 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2742. Min Range: -3.2742
Max Act: 3.0696. Min Act: -0.1700
Data Index: 7551806 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2742. Min Range: -3.2742
Max Act: 3.0854. Min Act: -0.1700
Data Index: 6028169 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19