Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 331 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9542. Min Range: -4.9542
Max Act: 4.9542. Min Act: -0.1700
Data Index: 6449871 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9542. Min Range: -4.9542
Max Act: 4.8917. Min Act: -0.1700
Data Index: 6883888 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9542. Min Range: -4.9542
Max Act: 4.8917. Min Act: -0.1700
Data Index: 88898 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9542. Min Range: -4.9542
Max Act: 4.8292. Min Act: -0.1699
Data Index: 88875 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9542. Min Range: -4.9542
Max Act: 4.8604. Min Act: -0.1700
Data Index: 7240972 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9542. Min Range: -4.9542
Max Act: 4.8292. Min Act: -0.1700
Data Index: 447037 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9542. Min Range: -4.9542
Max Act: 4.7979. Min Act: -0.1644
Data Index: 6449872 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9542. Min Range: -4.9542
Max Act: 4.8292. Min Act: -0.1700
Data Index: 88891 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9542. Min Range: -4.9542
Max Act: 4.8292. Min Act: -0.1695
Data Index: 6883894 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9542. Min Range: -4.9542
Max Act: 4.8292. Min Act: -0.1700
Data Index: 6865114 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9542. Min Range: -4.9542
Max Act: 4.7979. Min Act: -0.1689
Data Index: 6449869 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9542. Min Range: -4.9542
Max Act: 4.7667. Min Act: -0.1700
Data Index: 901478 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9542. Min Range: -4.9542
Max Act: 4.7667. Min Act: -0.1700
Data Index: 6472865 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9542. Min Range: -4.9542
Max Act: 4.7354. Min Act: -0.1700
Data Index: 4466284 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9542. Min Range: -4.9542
Max Act: 4.7667. Min Act: -0.1700
Data Index: 2576560 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9542. Min Range: -4.9542
Max Act: 4.7354. Min Act: -0.1700
Data Index: 6449873 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9542. Min Range: -4.9542
Max Act: 4.7354. Min Act: -0.1700
Data Index: 1476058 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9542. Min Range: -4.9542
Max Act: 4.7042. Min Act: -0.1700
Data Index: 5028256 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9542. Min Range: -4.9542
Max Act: 4.7354. Min Act: -0.1700
Data Index: 6566823 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9542. Min Range: -4.9542
Max Act: 4.7354. Min Act: -0.1700
Data Index: 1256161 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #19