Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2539 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1534. Min Range: -2.1534
Max Act: 2.1534. Min Act: -0.1700
Data Index: 3921538 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1534. Min Range: -2.1534
Max Act: 2.0530. Min Act: -0.1700
Data Index: 724503 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1534. Min Range: -2.1534
Max Act: 2.0361. Min Act: -0.1700
Data Index: 430174 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1534. Min Range: -2.1534
Max Act: 2.0024. Min Act: -0.1700
Data Index: 1858928 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1534. Min Range: -2.1534
Max Act: 2.0024. Min Act: -0.1700
Data Index: 3119679 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1534. Min Range: -2.1534
Max Act: 2.0024. Min Act: -0.1700
Data Index: 6776891 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1534. Min Range: -2.1534
Max Act: 1.9686. Min Act: -0.1700
Data Index: 82549 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1534. Min Range: -2.1534
Max Act: 1.9686. Min Act: -0.1700
Data Index: 3543845 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1534. Min Range: -2.1534
Max Act: 1.9686. Min Act: -0.1700
Data Index: 6970627 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1534. Min Range: -2.1534
Max Act: 1.9686. Min Act: -0.1700
Data Index: 4067228 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1534. Min Range: -2.1534
Max Act: 1.9516. Min Act: -0.1700
Data Index: 8185271 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1534. Min Range: -2.1534
Max Act: 1.9516. Min Act: -0.1700
Data Index: 2078159 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1534. Min Range: -2.1534
Max Act: 1.9686. Min Act: -0.1700
Data Index: 2502679 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1534. Min Range: -2.1534
Max Act: 1.9346. Min Act: -0.1700
Data Index: 1075157 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1534. Min Range: -2.1534
Max Act: 1.9346. Min Act: -0.1700
Data Index: 2979610 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1534. Min Range: -2.1534
Max Act: 1.9516. Min Act: -0.1700
Data Index: 3858756 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1534. Min Range: -2.1534
Max Act: 1.9516. Min Act: -0.1700
Data Index: 4156071 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1534. Min Range: -2.1534
Max Act: 1.9516. Min Act: -0.1700
Data Index: 4018184 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1534. Min Range: -2.1534
Max Act: 1.9516. Min Act: -0.1700
Data Index: 3661234 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1534. Min Range: -2.1534
Max Act: 1.9346. Min Act: -0.1700
Data Index: 3706295 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19