Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3809 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5033. Min Range: -5.5033
Max Act: 5.5033. Min Act: -0.1700
Data Index: 80235 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5033. Min Range: -5.5033
Max Act: 5.4096. Min Act: -0.1700
Data Index: 5651572 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5033. Min Range: -5.5033
Max Act: 5.1596. Min Act: -0.1700
Data Index: 8751921 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5033. Min Range: -5.5033
Max Act: 5.1908. Min Act: -0.1700
Data Index: 1211973 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5033. Min Range: -5.5033
Max Act: 5.2221. Min Act: -0.1700
Data Index: 7128381 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5033. Min Range: -5.5033
Max Act: 5.1908. Min Act: -0.1700
Data Index: 7604418 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5033. Min Range: -5.5033
Max Act: 5.1596. Min Act: -0.1700
Data Index: 7144991 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5033. Min Range: -5.5033
Max Act: 5.1596. Min Act: -0.1700
Data Index: 1831886 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5033. Min Range: -5.5033
Max Act: 5.1596. Min Act: -0.1700
Data Index: 5693319 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5033. Min Range: -5.5033
Max Act: 5.0971. Min Act: -0.1700
Data Index: 7033669 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5033. Min Range: -5.5033
Max Act: 5.1283. Min Act: -0.1700
Data Index: 1061504 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5033. Min Range: -5.5033
Max Act: 5.1283. Min Act: -0.1700
Data Index: 2618673 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5033. Min Range: -5.5033
Max Act: 5.0971. Min Act: -0.1700
Data Index: 2005325 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5033. Min Range: -5.5033
Max Act: 5.0971. Min Act: -0.1700
Data Index: 8003412 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5033. Min Range: -5.5033
Max Act: 5.0971. Min Act: -0.1700
Data Index: 1513761 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5033. Min Range: -5.5033
Max Act: 5.0971. Min Act: -0.1700
Data Index: 5534465 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5033. Min Range: -5.5033
Max Act: 5.0658. Min Act: -0.1700
Data Index: 2697015 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5033. Min Range: -5.5033
Max Act: 5.0658. Min Act: -0.1700
Data Index: 3530693 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5033. Min Range: -5.5033
Max Act: 5.0658. Min Act: -0.1700
Data Index: 5035234 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5033. Min Range: -5.5033
Max Act: 5.0658. Min Act: -0.1700
Data Index: 4415171 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19