Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3517 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8212. Min Range: -3.8212
Max Act: 3.8212. Min Act: -0.1700
Data Index: 599028 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8212. Min Range: -3.8212
Max Act: 3.7587. Min Act: -0.1700
Data Index: 8507969 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8212. Min Range: -3.8212
Max Act: 3.6961. Min Act: -0.1700
Data Index: 8320705 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8212. Min Range: -3.8212
Max Act: 3.6336. Min Act: -0.1700
Data Index: 6863325 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8212. Min Range: -3.8212
Max Act: 3.6648. Min Act: -0.1700
Data Index: 8005070 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8212. Min Range: -3.8212
Max Act: 3.6648. Min Act: -0.1700
Data Index: 1561121 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8212. Min Range: -3.8212
Max Act: 3.6336. Min Act: -0.1700
Data Index: 17304 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8212. Min Range: -3.8212
Max Act: 3.6648. Min Act: -0.1700
Data Index: 5934538 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8212. Min Range: -3.8212
Max Act: 3.6336. Min Act: -0.1700
Data Index: 286093 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8212. Min Range: -3.8212
Max Act: 3.6336. Min Act: -0.1700
Data Index: 6473774 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8212. Min Range: -3.8212
Max Act: 3.6336. Min Act: -0.1700
Data Index: 4717619 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8212. Min Range: -3.8212
Max Act: 3.6336. Min Act: -0.1700
Data Index: 1999315 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8212. Min Range: -3.8212
Max Act: 3.6336. Min Act: -0.1700
Data Index: 2739200 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8212. Min Range: -3.8212
Max Act: 3.6336. Min Act: -0.1700
Data Index: 5556071 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8212. Min Range: -3.8212
Max Act: 3.6023. Min Act: -0.1700
Data Index: 6229699 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8212. Min Range: -3.8212
Max Act: 3.6023. Min Act: -0.1700
Data Index: 2055732 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8212. Min Range: -3.8212
Max Act: 3.6023. Min Act: -0.1700
Data Index: 3938739 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8212. Min Range: -3.8212
Max Act: 3.6023. Min Act: -0.1700
Data Index: 3415211 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8212. Min Range: -3.8212
Max Act: 3.6023. Min Act: -0.1700
Data Index: 1999313 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8212. Min Range: -3.8212
Max Act: 3.6023. Min Act: -0.1700
Data Index: 3456397 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19