Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1937 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6747. Min Range: -3.6747
Max Act: 3.6747. Min Act: -0.1700
Data Index: 5845375 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6747. Min Range: -3.6747
Max Act: 3.6278. Min Act: -0.1700
Data Index: 8320426 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6747. Min Range: -3.6747
Max Act: 3.5809. Min Act: -0.1700
Data Index: 8420681 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6747. Min Range: -3.6747
Max Act: 3.5495. Min Act: -0.1700
Data Index: 1349051 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6747. Min Range: -3.6747
Max Act: 3.5339. Min Act: -0.1700
Data Index: 5074118 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6747. Min Range: -3.6747
Max Act: 3.5495. Min Act: -0.1700
Data Index: 2306096 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6747. Min Range: -3.6747
Max Act: 3.5339. Min Act: -0.1700
Data Index: 1484197 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6747. Min Range: -3.6747
Max Act: 3.5026. Min Act: -0.1700
Data Index: 6081482 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6747. Min Range: -3.6747
Max Act: 3.5026. Min Act: -0.1700
Data Index: 654887 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6747. Min Range: -3.6747
Max Act: 3.5026. Min Act: -0.1700
Data Index: 6334044 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6747. Min Range: -3.6747
Max Act: 3.5026. Min Act: -0.1700
Data Index: 5696300 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6747. Min Range: -3.6747
Max Act: 3.4869. Min Act: -0.1700
Data Index: 6370321 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6747. Min Range: -3.6747
Max Act: 3.4869. Min Act: -0.1700
Data Index: 8807939 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6747. Min Range: -3.6747
Max Act: 3.4869. Min Act: -0.1700
Data Index: 8092327 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6747. Min Range: -3.6747
Max Act: 3.4712. Min Act: -0.1700
Data Index: 4557245 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6747. Min Range: -3.6747
Max Act: 3.4556. Min Act: -0.1700
Data Index: 6730668 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6747. Min Range: -3.6747
Max Act: 3.4712. Min Act: -0.1700
Data Index: 1475968 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6747. Min Range: -3.6747
Max Act: 3.4556. Min Act: -0.1700
Data Index: 6138477 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6747. Min Range: -3.6747
Max Act: 3.4556. Min Act: -0.1700
Data Index: 2727219 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6747. Min Range: -3.6747
Max Act: 3.4712. Min Act: -0.1700
Data Index: 1709939 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19