Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3555 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2053. Min Range: -4.2053
Max Act: 4.2053. Min Act: -0.1700
Data Index: 1049833 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2053. Min Range: -4.2053
Max Act: 4.1115. Min Act: -0.1700
Data Index: 5050452 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2053. Min Range: -4.2053
Max Act: 4.0490. Min Act: -0.1700
Data Index: 7517606 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2053. Min Range: -4.2053
Max Act: 4.0490. Min Act: -0.1700
Data Index: 3211021 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2053. Min Range: -4.2053
Max Act: 4.0490. Min Act: -0.1700
Data Index: 8485201 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2053. Min Range: -4.2053
Max Act: 4.0178. Min Act: -0.1700
Data Index: 620511 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2053. Min Range: -4.2053
Max Act: 4.0178. Min Act: -0.1700
Data Index: 8463428 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2053. Min Range: -4.2053
Max Act: 3.9865. Min Act: -0.1700
Data Index: 2014150 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2053. Min Range: -4.2053
Max Act: 3.9552. Min Act: -0.1700
Data Index: 4201775 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2053. Min Range: -4.2053
Max Act: 4.0178. Min Act: -0.1700
Data Index: 6040131 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2053. Min Range: -4.2053
Max Act: 3.9865. Min Act: -0.1700
Data Index: 4746218 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2053. Min Range: -4.2053
Max Act: 3.9865. Min Act: -0.1700
Data Index: 270994 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2053. Min Range: -4.2053
Max Act: 3.9552. Min Act: -0.1700
Data Index: 3315500 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2053. Min Range: -4.2053
Max Act: 3.9552. Min Act: -0.1700
Data Index: 5168930 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2053. Min Range: -4.2053
Max Act: 3.9865. Min Act: -0.1700
Data Index: 5625864 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2053. Min Range: -4.2053
Max Act: 3.9552. Min Act: -0.1700
Data Index: 2418178 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2053. Min Range: -4.2053
Max Act: 3.9240. Min Act: -0.1700
Data Index: 5720242 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2053. Min Range: -4.2053
Max Act: 3.9552. Min Act: -0.1700
Data Index: 4520905 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2053. Min Range: -4.2053
Max Act: 3.9552. Min Act: -0.1700
Data Index: 6305897 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2053. Min Range: -4.2053
Max Act: 3.9552. Min Act: -0.1700
Data Index: 2559398 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19