Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 404 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0284. Min Range: -5.0284
Max Act: 5.0284. Min Act: -0.1700
Data Index: 1714545 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0284. Min Range: -5.0284
Max Act: 4.6221. Min Act: -0.1700
Data Index: 840203 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0284. Min Range: -5.0284
Max Act: 4.5284. Min Act: -0.1700
Data Index: 4286762 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0284. Min Range: -5.0284
Max Act: 4.5596. Min Act: -0.1700
Data Index: 3417119 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0284. Min Range: -5.0284
Max Act: 4.4971. Min Act: -0.1700
Data Index: 5964130 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0284. Min Range: -5.0284
Max Act: 4.4659. Min Act: -0.1700
Data Index: 8663686 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0284. Min Range: -5.0284
Max Act: 4.4034. Min Act: -0.1700
Data Index: 1014880 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0284. Min Range: -5.0284
Max Act: 4.4034. Min Act: -0.1700
Data Index: 4091162 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0284. Min Range: -5.0284
Max Act: 4.4034. Min Act: -0.1700
Data Index: 1234167 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0284. Min Range: -5.0284
Max Act: 4.3721. Min Act: -0.1700
Data Index: 41132 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0284. Min Range: -5.0284
Max Act: 4.3721. Min Act: -0.1700
Data Index: 1233436 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0284. Min Range: -5.0284
Max Act: 4.3721. Min Act: -0.1700
Data Index: 3417114 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0284. Min Range: -5.0284
Max Act: 4.3721. Min Act: -0.1700
Data Index: 6036906 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0284. Min Range: -5.0284
Max Act: 4.3409. Min Act: -0.1700
Data Index: 7241700 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0284. Min Range: -5.0284
Max Act: 4.3409. Min Act: -0.1700
Data Index: 1708005 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0284. Min Range: -5.0284
Max Act: 4.3409. Min Act: -0.1700
Data Index: 7219746 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0284. Min Range: -5.0284
Max Act: 4.3409. Min Act: -0.1700
Data Index: 3969620 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0284. Min Range: -5.0284
Max Act: 4.3409. Min Act: -0.1700
Data Index: 6475639 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0284. Min Range: -5.0284
Max Act: 4.3409. Min Act: -0.1700
Data Index: 430021 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0284. Min Range: -5.0284
Max Act: 4.3096. Min Act: -0.1700
Data Index: 2642724 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19