Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5117 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3722. Min Range: -7.3722
Max Act: 7.3722. Min Act: -0.1700
Data Index: 4914119 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.4034. Min Act: -0.1700
Data Index: 2919888 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.4347. Min Act: -0.1700
Data Index: 6890333 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.3722. Min Act: -0.1700
Data Index: 5365416 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.3722. Min Act: -0.1700
Data Index: 7550905 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.2472. Min Act: -0.1700
Data Index: 2537189 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.2784. Min Act: -0.1700
Data Index: 1405233 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.2472. Min Act: -0.1700
Data Index: 7243556 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.2159. Min Act: -0.1700
Data Index: 3082723 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.2472. Min Act: -0.1700
Data Index: 7816625 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.2159. Min Act: -0.1700
Data Index: 7613867 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.1847. Min Act: -0.1700
Data Index: 1277245 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.2159. Min Act: -0.1700
Data Index: 3407089 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.1847. Min Act: -0.1700
Data Index: 6879677 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.1534. Min Act: -0.1700
Data Index: 2321781 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.1534. Min Act: -0.1700
Data Index: 1417046 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.1534. Min Act: -0.1700
Data Index: 4732123 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.1534. Min Act: -0.1700
Data Index: 8745990 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.1534. Min Act: -0.1700
Data Index: 3210833 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.1222. Min Act: -0.1700
Data Index: 4851106 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19