Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2017 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7762. Min Range: -5.7762
Max Act: 5.7762. Min Act: -0.1700
Data Index: 2890650 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7762. Min Range: -5.7762
Max Act: 5.6825. Min Act: -0.1700
Data Index: 8301326 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7762. Min Range: -5.7762
Max Act: 5.6512. Min Act: -0.1700
Data Index: 7162062 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7762. Min Range: -5.7762
Max Act: 5.6200. Min Act: -0.1700
Data Index: 3886051 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7762. Min Range: -5.7762
Max Act: 5.5262. Min Act: -0.1700
Data Index: 8668156 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7762. Min Range: -5.7762
Max Act: 5.4325. Min Act: -0.1700
Data Index: 8268769 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7762. Min Range: -5.7762
Max Act: 5.4325. Min Act: -0.1700
Data Index: 7727462 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7762. Min Range: -5.7762
Max Act: 5.3700. Min Act: -0.1700
Data Index: 6931532 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7762. Min Range: -5.7762
Max Act: 5.3387. Min Act: -0.1700
Data Index: 936594 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7762. Min Range: -5.7762
Max Act: 5.3075. Min Act: -0.1700
Data Index: 5423157 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7762. Min Range: -5.7762
Max Act: 5.3075. Min Act: -0.1700
Data Index: 5775191 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7762. Min Range: -5.7762
Max Act: 5.3075. Min Act: -0.1700
Data Index: 8644382 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7762. Min Range: -5.7762
Max Act: 5.2762. Min Act: -0.1700
Data Index: 7827025 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7762. Min Range: -5.7762
Max Act: 5.2762. Min Act: -0.1700
Data Index: 5329288 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7762. Min Range: -5.7762
Max Act: 5.2762. Min Act: -0.1700
Data Index: 1613384 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7762. Min Range: -5.7762
Max Act: 5.2762. Min Act: -0.1700
Data Index: 8580085 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7762. Min Range: -5.7762
Max Act: 5.2762. Min Act: -0.1700
Data Index: 2626929 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7762. Min Range: -5.7762
Max Act: 5.2762. Min Act: -0.1700
Data Index: 7150154 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7762. Min Range: -5.7762
Max Act: 5.2137. Min Act: -0.1700
Data Index: 1337563 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7762. Min Range: -5.7762
Max Act: 5.1825. Min Act: -0.1700
Data Index: 3626737 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19