Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2643 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7105. Min Range: -7.7105
Max Act: 7.7105. Min Act: -0.1700
Data Index: 8523561 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7105. Min Range: -7.7105
Max Act: 7.5542. Min Act: -0.1700
Data Index: 4867792 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7105. Min Range: -7.7105
Max Act: 7.4917. Min Act: -0.1700
Data Index: 4203002 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7105. Min Range: -7.7105
Max Act: 7.4917. Min Act: -0.1700
Data Index: 1532956 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7105. Min Range: -7.7105
Max Act: 7.4292. Min Act: -0.1700
Data Index: 1305021 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7105. Min Range: -7.7105
Max Act: 7.3980. Min Act: -0.1700
Data Index: 5954400 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7105. Min Range: -7.7105
Max Act: 7.3667. Min Act: -0.1700
Data Index: 5213811 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7105. Min Range: -7.7105
Max Act: 7.3042. Min Act: -0.1700
Data Index: 1265902 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7105. Min Range: -7.7105
Max Act: 7.2730. Min Act: -0.1700
Data Index: 2568725 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7105. Min Range: -7.7105
Max Act: 7.2417. Min Act: -0.1700
Data Index: 7798769 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7105. Min Range: -7.7105
Max Act: 7.2417. Min Act: -0.1700
Data Index: 142311 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7105. Min Range: -7.7105
Max Act: 7.2105. Min Act: -0.1700
Data Index: 3517912 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7105. Min Range: -7.7105
Max Act: 7.2105. Min Act: -0.1700
Data Index: 1588716 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7105. Min Range: -7.7105
Max Act: 7.1792. Min Act: -0.1700
Data Index: 7123925 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7105. Min Range: -7.7105
Max Act: 7.1792. Min Act: -0.1700
Data Index: 3151153 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7105. Min Range: -7.7105
Max Act: 7.1480. Min Act: -0.1700
Data Index: 5566315 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7105. Min Range: -7.7105
Max Act: 7.1167. Min Act: -0.1700
Data Index: 4222563 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7105. Min Range: -7.7105
Max Act: 7.1480. Min Act: -0.1700
Data Index: 428027 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7105. Min Range: -7.7105
Max Act: 7.1167. Min Act: -0.1700
Data Index: 7525061 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7105. Min Range: -7.7105
Max Act: 7.0855. Min Act: -0.1700
Data Index: 3430061 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19