Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 27 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0678. Min Range: -7.0678
Max Act: 7.0678. Min Act: -0.1700
Data Index: 4959213 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0678. Min Range: -7.0678
Max Act: 6.9116. Min Act: -0.1700
Data Index: 7401849 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0678. Min Range: -7.0678
Max Act: 6.6616. Min Act: -0.1700
Data Index: 5298029 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0678. Min Range: -7.0678
Max Act: 6.5366. Min Act: -0.1700
Data Index: 6277233 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0678. Min Range: -7.0678
Max Act: 6.5366. Min Act: -0.1700
Data Index: 4926907 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0678. Min Range: -7.0678
Max Act: 6.5053. Min Act: -0.1700
Data Index: 156513 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0678. Min Range: -7.0678
Max Act: 6.5053. Min Act: -0.1700
Data Index: 7129580 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0678. Min Range: -7.0678
Max Act: 6.5053. Min Act: -0.1700
Data Index: 553507 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0678. Min Range: -7.0678
Max Act: 6.4428. Min Act: -0.1700
Data Index: 7869254 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0678. Min Range: -7.0678
Max Act: 6.4428. Min Act: -0.1700
Data Index: 2299023 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0678. Min Range: -7.0678
Max Act: 6.4116. Min Act: -0.1700
Data Index: 5419369 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0678. Min Range: -7.0678
Max Act: 6.4116. Min Act: -0.1700
Data Index: 2095949 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0678. Min Range: -7.0678
Max Act: 6.3491. Min Act: -0.1700
Data Index: 7354219 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0678. Min Range: -7.0678
Max Act: 6.3178. Min Act: -0.1700
Data Index: 2386112 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0678. Min Range: -7.0678
Max Act: 6.3178. Min Act: -0.1700
Data Index: 3042239 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0678. Min Range: -7.0678
Max Act: 6.2866. Min Act: -0.1700
Data Index: 3499755 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0678. Min Range: -7.0678
Max Act: 6.2866. Min Act: -0.1700
Data Index: 3517831 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0678. Min Range: -7.0678
Max Act: 6.2553. Min Act: -0.1700
Data Index: 6405743 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0678. Min Range: -7.0678
Max Act: 6.2553. Min Act: -0.1700
Data Index: 1441089 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0678. Min Range: -7.0678
Max Act: 6.2553. Min Act: -0.1700
Data Index: 7777109 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19