Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4478 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0675. Min Range: -5.0675
Max Act: 5.0675. Min Act: -0.1700
Data Index: 2161806 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.9425. Min Act: -0.1700
Data Index: 1406100 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.8175. Min Act: -0.1700
Data Index: 1589351 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.8175. Min Act: -0.1700
Data Index: 6916333 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.6925. Min Act: -0.1700
Data Index: 5719226 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.6925. Min Act: -0.1700
Data Index: 972060 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.6300. Min Act: -0.1700
Data Index: 2079729 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.6612. Min Act: -0.1700
Data Index: 6487058 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.5987. Min Act: -0.1700
Data Index: 2206659 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.5675. Min Act: -0.1700
Data Index: 4590744 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.5675. Min Act: -0.1700
Data Index: 579742 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.5675. Min Act: -0.1700
Data Index: 6536778 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.5675. Min Act: -0.1700
Data Index: 7564610 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.5362. Min Act: -0.1700
Data Index: 2776473 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.5362. Min Act: -0.1700
Data Index: 2784536 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.5050. Min Act: -0.1700
Data Index: 4165265 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.5050. Min Act: -0.1700
Data Index: 5979314 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.5050. Min Act: -0.1700
Data Index: 4539540 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.5050. Min Act: -0.1700
Data Index: 1570004 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.5050. Min Act: -0.1700
Data Index: 7431836 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19