Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5410 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0148. Min Range: -5.0148
Max Act: 5.0148. Min Act: -0.1700
Data Index: 8357908 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.9523. Min Act: -0.1700
Data Index: 1590178 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.9523. Min Act: -0.1700
Data Index: 8705876 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.8273. Min Act: -0.1700
Data Index: 6277228 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.8273. Min Act: -0.1700
Data Index: 966880 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.7960. Min Act: -0.1700
Data Index: 454337 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.7648. Min Act: -0.1700
Data Index: 7293271 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.7023. Min Act: -0.1700
Data Index: 4652863 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.7023. Min Act: -0.1700
Data Index: 554052 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.6710. Min Act: -0.1700
Data Index: 5646033 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.7023. Min Act: -0.1700
Data Index: 3925251 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.6710. Min Act: -0.1700
Data Index: 6037007 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.6398. Min Act: -0.1700
Data Index: 1902565 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.6398. Min Act: -0.1700
Data Index: 4957872 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.6085. Min Act: -0.1700
Data Index: 4989005 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.6398. Min Act: -0.1700
Data Index: 6037006 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.6398. Min Act: -0.1700
Data Index: 3357933 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.6398. Min Act: -0.1700
Data Index: 1196825 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.6398. Min Act: -0.1700
Data Index: 6749758 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.6085. Min Act: -0.1700
Data Index: 4519156 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19