Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3359 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4291. Min Range: -9.4291
Max Act: 9.4291. Min Act: -0.1700
Data Index: 6237326 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4291. Min Range: -9.4291
Max Act: 9.4291. Min Act: -0.1700
Data Index: 7687229 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4291. Min Range: -9.4291
Max Act: 9.2416. Min Act: -0.1700
Data Index: 1679333 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4291. Min Range: -9.4291
Max Act: 9.2416. Min Act: -0.1700
Data Index: 716770 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4291. Min Range: -9.4291
Max Act: 9.1791. Min Act: -0.1700
Data Index: 6123888 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4291. Min Range: -9.4291
Max Act: 9.1166. Min Act: -0.1700
Data Index: 6776422 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4291. Min Range: -9.4291
Max Act: 9.1166. Min Act: -0.1700
Data Index: 413894 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4291. Min Range: -9.4291
Max Act: 9.1166. Min Act: -0.1700
Data Index: 5178738 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4291. Min Range: -9.4291
Max Act: 9.1166. Min Act: -0.1700
Data Index: 7466061 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4291. Min Range: -9.4291
Max Act: 9.1166. Min Act: -0.1700
Data Index: 1094191 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4291. Min Range: -9.4291
Max Act: 9.0541. Min Act: -0.1700
Data Index: 1924173 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4291. Min Range: -9.4291
Max Act: 8.9916. Min Act: -0.1700
Data Index: 5413890 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4291. Min Range: -9.4291
Max Act: 8.9916. Min Act: -0.1700
Data Index: 5591970 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4291. Min Range: -9.4291
Max Act: 8.9916. Min Act: -0.1700
Data Index: 7392851 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4291. Min Range: -9.4291
Max Act: 8.9916. Min Act: -0.1700
Data Index: 5990497 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4291. Min Range: -9.4291
Max Act: 8.9916. Min Act: -0.1700
Data Index: 8460356 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4291. Min Range: -9.4291
Max Act: 8.9916. Min Act: -0.1700
Data Index: 26276 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4291. Min Range: -9.4291
Max Act: 8.9916. Min Act: -0.1700
Data Index: 6177246 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4291. Min Range: -9.4291
Max Act: 8.9291. Min Act: -0.1700
Data Index: 4800108 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4291. Min Range: -9.4291
Max Act: 8.9291. Min Act: -0.1700
Data Index: 5685004 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19