Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2949 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.6619. Min Act: -0.1700
Data Index: 2173507 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.6619. Min Act: -0.1700
Data Index: 1047726 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.3806. Min Act: -0.1700
Data Index: 7168366 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.3181. Min Act: -0.1700
Data Index: 5405186 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.2556. Min Act: -0.1700
Data Index: 3282149 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.2244. Min Act: -0.1700
Data Index: 7900252 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.2244. Min Act: -0.1700
Data Index: 7595273 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.1619. Min Act: -0.1700
Data Index: 147103 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.1931. Min Act: -0.1700
Data Index: 7030713 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.1306. Min Act: -0.1700
Data Index: 5201715 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.1306. Min Act: -0.1700
Data Index: 7455166 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.1306. Min Act: -0.1700
Data Index: 1499937 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.1306. Min Act: -0.1700
Data Index: 5675798 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.0994. Min Act: -0.1700
Data Index: 7700895 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.0994. Min Act: -0.1700
Data Index: 2095743 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.0681. Min Act: -0.1700
Data Index: 7782638 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.0681. Min Act: -0.1700
Data Index: 3486706 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.0681. Min Act: -0.1700
Data Index: 2837547 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.0681. Min Act: -0.1700
Data Index: 5622633 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.0369. Min Act: -0.1700
Data Index: 8583840 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19