Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1251 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.2867. Min Act: -0.1700
Data Index: 8390306 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.2867. Min Act: -0.1700
Data Index: 1152231 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.2242. Min Act: -0.1700
Data Index: 2965847 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.1930. Min Act: -0.1700
Data Index: 1426932 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0992. Min Act: -0.1700
Data Index: 8458564 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0367. Min Act: -0.1700
Data Index: 7290639 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0680. Min Act: -0.1700
Data Index: 6245085 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2867. Min Range: -5.2867
Max Act: 4.9430. Min Act: -0.1700
Data Index: 3152181 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2867. Min Range: -5.2867
Max Act: 4.9117. Min Act: -0.1700
Data Index: 3882056 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2867. Min Range: -5.2867
Max Act: 4.9117. Min Act: -0.1700
Data Index: 3896050 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2867. Min Range: -5.2867
Max Act: 4.9117. Min Act: -0.1700
Data Index: 1754336 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2867. Min Range: -5.2867
Max Act: 4.8805. Min Act: -0.1700
Data Index: 796715 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2867. Min Range: -5.2867
Max Act: 4.8492. Min Act: -0.1700
Data Index: 5637630 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2867. Min Range: -5.2867
Max Act: 4.8492. Min Act: -0.1700
Data Index: 986169 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2867. Min Range: -5.2867
Max Act: 4.8805. Min Act: -0.1700
Data Index: 8536292 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2867. Min Range: -5.2867
Max Act: 4.8805. Min Act: -0.1700
Data Index: 6663223 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2867. Min Range: -5.2867
Max Act: 4.7867. Min Act: -0.1700
Data Index: 7865653 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2867. Min Range: -5.2867
Max Act: 4.8492. Min Act: -0.1700
Data Index: 6363133 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2867. Min Range: -5.2867
Max Act: 4.7867. Min Act: -0.1700
Data Index: 6234781 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2867. Min Range: -5.2867
Max Act: 4.7867. Min Act: -0.1700
Data Index: 1417287 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19