Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4197 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2808. Min Range: -5.2808
Max Act: 5.2808. Min Act: -0.1700
Data Index: 1365383 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2808. Min Range: -5.2808
Max Act: 5.1558. Min Act: -0.1700
Data Index: 2429934 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2808. Min Range: -5.2808
Max Act: 5.0933. Min Act: -0.1700
Data Index: 4224856 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2808. Min Range: -5.2808
Max Act: 5.0308. Min Act: -0.1700
Data Index: 5063635 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2808. Min Range: -5.2808
Max Act: 5.0308. Min Act: -0.1700
Data Index: 2205843 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2808. Min Range: -5.2808
Max Act: 4.9995. Min Act: -0.1700
Data Index: 2881491 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2808. Min Range: -5.2808
Max Act: 4.9995. Min Act: -0.1700
Data Index: 5734422 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2808. Min Range: -5.2808
Max Act: 4.9683. Min Act: -0.1700
Data Index: 4654015 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2808. Min Range: -5.2808
Max Act: 4.9683. Min Act: -0.1700
Data Index: 269450 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2808. Min Range: -5.2808
Max Act: 4.9683. Min Act: -0.1700
Data Index: 7881865 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2808. Min Range: -5.2808
Max Act: 4.9370. Min Act: -0.1700
Data Index: 1438811 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2808. Min Range: -5.2808
Max Act: 4.9370. Min Act: -0.1700
Data Index: 8299459 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2808. Min Range: -5.2808
Max Act: 4.9058. Min Act: -0.1700
Data Index: 3787207 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2808. Min Range: -5.2808
Max Act: 4.9370. Min Act: -0.1700
Data Index: 444567 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2808. Min Range: -5.2808
Max Act: 4.9370. Min Act: -0.1700
Data Index: 7593735 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2808. Min Range: -5.2808
Max Act: 4.9058. Min Act: -0.1700
Data Index: 2923098 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2808. Min Range: -5.2808
Max Act: 4.8745. Min Act: -0.1700
Data Index: 6411347 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2808. Min Range: -5.2808
Max Act: 4.8745. Min Act: -0.1700
Data Index: 6541429 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2808. Min Range: -5.2808
Max Act: 4.8745. Min Act: -0.1700
Data Index: 539457 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2808. Min Range: -5.2808
Max Act: 4.8745. Min Act: -0.1700
Data Index: 5840453 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19