Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2866 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6117. Min Range: -8.6117
Max Act: 8.6117. Min Act: -0.1700
Data Index: 4918380 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6117. Min Range: -8.6117
Max Act: 8.4242. Min Act: -0.1700
Data Index: 7788692 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6117. Min Range: -8.6117
Max Act: 8.2992. Min Act: -0.1700
Data Index: 3467225 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6117. Min Range: -8.6117
Max Act: 8.2992. Min Act: -0.1700
Data Index: 1698406 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6117. Min Range: -8.6117
Max Act: 8.2992. Min Act: -0.1700
Data Index: 2996215 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6117. Min Range: -8.6117
Max Act: 8.2992. Min Act: -0.1700
Data Index: 625331 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6117. Min Range: -8.6117
Max Act: 8.2992. Min Act: -0.1700
Data Index: 3953858 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6117. Min Range: -8.6117
Max Act: 8.2367. Min Act: -0.1700
Data Index: 6028964 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6117. Min Range: -8.6117
Max Act: 8.1117. Min Act: -0.1700
Data Index: 1792078 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6117. Min Range: -8.6117
Max Act: 8.1117. Min Act: -0.1700
Data Index: 6438773 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6117. Min Range: -8.6117
Max Act: 8.1117. Min Act: -0.1700
Data Index: 2575553 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6117. Min Range: -8.6117
Max Act: 8.0492. Min Act: -0.1700
Data Index: 3603053 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6117. Min Range: -8.6117
Max Act: 7.9242. Min Act: -0.1700
Data Index: 1461676 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6117. Min Range: -8.6117
Max Act: 7.8617. Min Act: -0.1700
Data Index: 5423209 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6117. Min Range: -8.6117
Max Act: 7.8617. Min Act: -0.1700
Data Index: 5199270 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6117. Min Range: -8.6117
Max Act: 7.7992. Min Act: -0.1700
Data Index: 3450927 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6117. Min Range: -8.6117
Max Act: 7.7992. Min Act: -0.1700
Data Index: 3565716 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6117. Min Range: -8.6117
Max Act: 7.7992. Min Act: -0.1700
Data Index: 5797325 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6117. Min Range: -8.6117
Max Act: 7.7992. Min Act: -0.1700
Data Index: 2811852 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6117. Min Range: -8.6117
Max Act: 7.7680. Min Act: -0.1700
Data Index: 4670927 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19