Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1857 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5522. Min Range: -5.5522
Max Act: 5.5522. Min Act: -0.1700
Data Index: 119604 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5522. Min Range: -5.5522
Max Act: 5.3022. Min Act: -0.1700
Data Index: 3391229 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5522. Min Range: -5.5522
Max Act: 5.2085. Min Act: -0.1700
Data Index: 6948886 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5522. Min Range: -5.5522
Max Act: 5.1772. Min Act: -0.1700
Data Index: 854699 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5522. Min Range: -5.5522
Max Act: 5.1460. Min Act: -0.1700
Data Index: 6598048 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5522. Min Range: -5.5522
Max Act: 5.1147. Min Act: -0.1700
Data Index: 6034945 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5522. Min Range: -5.5522
Max Act: 5.1147. Min Act: -0.1700
Data Index: 7085581 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5522. Min Range: -5.5522
Max Act: 5.0835. Min Act: -0.1700
Data Index: 4779637 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5522. Min Range: -5.5522
Max Act: 5.0835. Min Act: -0.1700
Data Index: 235648 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5522. Min Range: -5.5522
Max Act: 5.0522. Min Act: -0.1700
Data Index: 1411342 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5522. Min Range: -5.5522
Max Act: 5.0210. Min Act: -0.1700
Data Index: 8806034 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5522. Min Range: -5.5522
Max Act: 5.0210. Min Act: -0.1700
Data Index: 8009987 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5522. Min Range: -5.5522
Max Act: 5.0210. Min Act: -0.1700
Data Index: 1909619 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5522. Min Range: -5.5522
Max Act: 4.9897. Min Act: -0.1700
Data Index: 5869575 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5522. Min Range: -5.5522
Max Act: 4.9585. Min Act: -0.1700
Data Index: 674748 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5522. Min Range: -5.5522
Max Act: 4.9272. Min Act: -0.1700
Data Index: 1507106 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5522. Min Range: -5.5522
Max Act: 4.9272. Min Act: -0.1700
Data Index: 7884362 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5522. Min Range: -5.5522
Max Act: 4.9272. Min Act: -0.1700
Data Index: 661579 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5522. Min Range: -5.5522
Max Act: 4.9272. Min Act: -0.1700
Data Index: 5573759 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5522. Min Range: -5.5522
Max Act: 4.9272. Min Act: -0.1700
Data Index: 4902801 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19