Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3706 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1847. Min Range: -4.1847
Max Act: 4.1847. Min Act: -0.1700
Data Index: 6154433 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1847. Min Range: -4.1847
Max Act: 4.1847. Min Act: -0.1700
Data Index: 4095307 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1847. Min Range: -4.1847
Max Act: 4.1534. Min Act: -0.1700
Data Index: 3366448 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1847. Min Range: -4.1847
Max Act: 4.1222. Min Act: -0.1700
Data Index: 6154435 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1847. Min Range: -4.1847
Max Act: 4.0597. Min Act: -0.1700
Data Index: 2486640 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1847. Min Range: -4.1847
Max Act: 4.0597. Min Act: -0.1700
Data Index: 6026465 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1847. Min Range: -4.1847
Max Act: 4.0597. Min Act: -0.1700
Data Index: 4067738 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1847. Min Range: -4.1847
Max Act: 4.0284. Min Act: -0.1700
Data Index: 1594876 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1847. Min Range: -4.1847
Max Act: 3.9972. Min Act: -0.1700
Data Index: 4349073 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1847. Min Range: -4.1847
Max Act: 3.9972. Min Act: -0.1700
Data Index: 1594875 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1847. Min Range: -4.1847
Max Act: 3.9659. Min Act: -0.1700
Data Index: 4095306 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1847. Min Range: -4.1847
Max Act: 3.9659. Min Act: -0.1700
Data Index: 5743816 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1847. Min Range: -4.1847
Max Act: 3.9659. Min Act: -0.1700
Data Index: 3713251 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1847. Min Range: -4.1847
Max Act: 3.9346. Min Act: -0.1700
Data Index: 3339067 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1847. Min Range: -4.1847
Max Act: 3.9346. Min Act: -0.1700
Data Index: 256547 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1847. Min Range: -4.1847
Max Act: 3.9346. Min Act: -0.1700
Data Index: 4146886 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1847. Min Range: -4.1847
Max Act: 3.9346. Min Act: -0.1700
Data Index: 6763434 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1847. Min Range: -4.1847
Max Act: 3.9034. Min Act: -0.1700
Data Index: 8638045 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1847. Min Range: -4.1847
Max Act: 3.9346. Min Act: -0.1700
Data Index: 4693618 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1847. Min Range: -4.1847
Max Act: 3.9034. Min Act: -0.1700
Data Index: 256548 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19