Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4015 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.3074. Min Act: -0.1700
Data Index: 3898333 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.2136. Min Act: -0.1700
Data Index: 6616705 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.1824. Min Act: -0.1700
Data Index: 7160709 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.1511. Min Act: -0.1700
Data Index: 6347341 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.1511. Min Act: -0.1700
Data Index: 5830589 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.1199. Min Act: -0.1700
Data Index: 5747581 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.1511. Min Act: -0.1700
Data Index: 2978078 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.1511. Min Act: -0.1700
Data Index: 4968800 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.1511. Min Act: -0.1700
Data Index: 2266753 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.1511. Min Act: -0.1700
Data Index: 4536277 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.1199. Min Act: -0.1700
Data Index: 2493103 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.0886. Min Act: -0.1700
Data Index: 4709058 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.1199. Min Act: -0.1700
Data Index: 5218569 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.1199. Min Act: -0.1700
Data Index: 4673205 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.1199. Min Act: -0.1700
Data Index: 351564 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.1199. Min Act: -0.1700
Data Index: 3094282 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.1199. Min Act: -0.1700
Data Index: 355558 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.1199. Min Act: -0.1700
Data Index: 1478670 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.1199. Min Act: -0.1700
Data Index: 4162534 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.1199. Min Act: -0.1700
Data Index: 4004759 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19