Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3530 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1580. Min Range: -6.1580
Max Act: 6.1580. Min Act: -0.1700
Data Index: 1389083 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1580. Min Range: -6.1580
Max Act: 5.9393. Min Act: -0.1700
Data Index: 8013422 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1580. Min Range: -6.1580
Max Act: 5.9393. Min Act: -0.1700
Data Index: 5423578 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1580. Min Range: -6.1580
Max Act: 5.8455. Min Act: -0.1700
Data Index: 1031884 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1580. Min Range: -6.1580
Max Act: 5.8455. Min Act: -0.1700
Data Index: 5485294 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1580. Min Range: -6.1580
Max Act: 5.8143. Min Act: -0.1700
Data Index: 43498 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1580. Min Range: -6.1580
Max Act: 5.8143. Min Act: -0.1700
Data Index: 1100606 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1580. Min Range: -6.1580
Max Act: 5.7830. Min Act: -0.1700
Data Index: 955363 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1580. Min Range: -6.1580
Max Act: 5.7205. Min Act: -0.1700
Data Index: 5230252 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1580. Min Range: -6.1580
Max Act: 5.6893. Min Act: -0.1700
Data Index: 554181 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1580. Min Range: -6.1580
Max Act: 5.6268. Min Act: -0.1700
Data Index: 6366049 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1580. Min Range: -6.1580
Max Act: 5.6893. Min Act: -0.1700
Data Index: 750186 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1580. Min Range: -6.1580
Max Act: 5.6580. Min Act: -0.1700
Data Index: 2677046 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1580. Min Range: -6.1580
Max Act: 5.6268. Min Act: -0.1700
Data Index: 3158903 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1580. Min Range: -6.1580
Max Act: 5.6580. Min Act: -0.1700
Data Index: 5060927 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1580. Min Range: -6.1580
Max Act: 5.6580. Min Act: -0.1700
Data Index: 7870216 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1580. Min Range: -6.1580
Max Act: 5.6580. Min Act: -0.1700
Data Index: 5206608 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1580. Min Range: -6.1580
Max Act: 5.6893. Min Act: -0.1700
Data Index: 4400850 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1580. Min Range: -6.1580
Max Act: 5.6268. Min Act: -0.1700
Data Index: 6429152 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1580. Min Range: -6.1580
Max Act: 5.6268. Min Act: -0.1700
Data Index: 7666026 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19