Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4127 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2144. Min Range: -5.2144
Max Act: 5.2144. Min Act: -0.1700
Data Index: 7642756 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2144. Min Range: -5.2144
Max Act: 5.1831. Min Act: -0.1700
Data Index: 5308164 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2144. Min Range: -5.2144
Max Act: 5.1206. Min Act: -0.1700
Data Index: 2885069 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2144. Min Range: -5.2144
Max Act: 5.1519. Min Act: -0.1700
Data Index: 1976671 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2144. Min Range: -5.2144
Max Act: 5.1206. Min Act: -0.1700
Data Index: 6266630 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2144. Min Range: -5.2144
Max Act: 5.1206. Min Act: -0.1700
Data Index: 2885071 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2144. Min Range: -5.2144
Max Act: 5.0581. Min Act: -0.1700
Data Index: 7149501 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2144. Min Range: -5.2144
Max Act: 5.0894. Min Act: -0.1700
Data Index: 2885073 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2144. Min Range: -5.2144
Max Act: 5.0581. Min Act: -0.1700
Data Index: 4167021 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2144. Min Range: -5.2144
Max Act: 5.0581. Min Act: -0.1700
Data Index: 4473271 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2144. Min Range: -5.2144
Max Act: 5.0581. Min Act: -0.1700
Data Index: 2481457 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.9956. Min Act: -0.1700
Data Index: 1793555 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2144. Min Range: -5.2144
Max Act: 5.0269. Min Act: -0.1700
Data Index: 5224711 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2144. Min Range: -5.2144
Max Act: 5.0269. Min Act: -0.1700
Data Index: 2907652 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2144. Min Range: -5.2144
Max Act: 5.0269. Min Act: -0.1700
Data Index: 4615130 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.9956. Min Act: -0.1700
Data Index: 4440407 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2144. Min Range: -5.2144
Max Act: 5.0269. Min Act: -0.1700
Data Index: 1790998 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2144. Min Range: -5.2144
Max Act: 5.0581. Min Act: -0.1700
Data Index: 1790999 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.9956. Min Act: -0.1700
Data Index: 3879535 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.9956. Min Act: -0.1700
Data Index: 4422501 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19