Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3901 in Layer 15
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: 3171099 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.9836. Min Act: -0.1700
Data Index: 2387234 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.9836. Min Act: -0.1700
Data Index: 6380366 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.9523. Min Act: -0.1700
Data Index: 3238750 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.9523. Min Act: -0.1700
Data Index: 3238766 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.9211. Min Act: -0.1700
Data Index: 2904202 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.8898. Min Act: -0.1700
Data Index: 3172984 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.8898. Min Act: -0.1700
Data Index: 8305000 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.8273. Min Act: -0.1700
Data Index: 680450 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.8586. Min Act: -0.1700
Data Index: 3263930 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.8586. Min Act: -0.1700
Data Index: 5048417 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.8586. Min Act: -0.1700
Data Index: 8464297 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.7961. Min Act: -0.1700
Data Index: 8389456 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.7648. Min Act: -0.1700
Data Index: 2331082 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.7648. Min Act: -0.1700
Data Index: 2585371 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.7336. Min Act: -0.1700
Data Index: 5821854 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.7336. Min Act: -0.1700
Data Index: 3055630 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.7336. Min Act: -0.1700
Data Index: 7749213 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.7336. Min Act: -0.1700
Data Index: 7681324 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0148. Min Range: -5.0148
Max Act: 4.7023. Min Act: -0.1700
Data Index: 4321139 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19