Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1163 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4524. Min Range: -2.4524
Max Act: 2.4524. Min Act: -0.1700
Data Index: 228349 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4524. Min Range: -2.4524
Max Act: 2.4035. Min Act: -0.1700
Data Index: 7658621 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4524. Min Range: -2.4524
Max Act: 2.4035. Min Act: -0.1700
Data Index: 8484000 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4524. Min Range: -2.4524
Max Act: 2.3872. Min Act: -0.1700
Data Index: 8353871 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4524. Min Range: -2.4524
Max Act: 2.3708. Min Act: -0.1700
Data Index: 7945260 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4524. Min Range: -2.4524
Max Act: 2.3708. Min Act: -0.1700
Data Index: 1418394 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4524. Min Range: -2.4524
Max Act: 2.3708. Min Act: -0.1700
Data Index: 3463469 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4524. Min Range: -2.4524
Max Act: 2.3708. Min Act: -0.1700
Data Index: 8147829 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4524. Min Range: -2.4524
Max Act: 2.3545. Min Act: -0.1700
Data Index: 2805954 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4524. Min Range: -2.4524
Max Act: 2.3545. Min Act: -0.1700
Data Index: 4498484 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4524. Min Range: -2.4524
Max Act: 2.3381. Min Act: -0.1700
Data Index: 6812103 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4524. Min Range: -2.4524
Max Act: 2.3381. Min Act: -0.1700
Data Index: 6845481 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4524. Min Range: -2.4524
Max Act: 2.3381. Min Act: -0.1700
Data Index: 8308999 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4524. Min Range: -2.4524
Max Act: 2.3381. Min Act: -0.1700
Data Index: 2191698 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4524. Min Range: -2.4524
Max Act: 2.3381. Min Act: -0.1700
Data Index: 3340968 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4524. Min Range: -2.4524
Max Act: 2.3217. Min Act: -0.1700
Data Index: 7235042 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4524. Min Range: -2.4524
Max Act: 2.3217. Min Act: -0.1700
Data Index: 918918 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4524. Min Range: -2.4524
Max Act: 2.3217. Min Act: -0.1700
Data Index: 6387478 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4524. Min Range: -2.4524
Max Act: 2.3217. Min Act: -0.1700
Data Index: 2887496 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4524. Min Range: -2.4524
Max Act: 2.3217. Min Act: -0.1700
Data Index: 4784597 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19