Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2849 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8032. Min Range: -1.8032
Max Act: 1.8032. Min Act: -0.1700
Data Index: 6198534 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8032. Min Range: -1.8032
Max Act: 1.7860. Min Act: -0.1700
Data Index: 304540 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8032. Min Range: -1.8032
Max Act: 1.7687. Min Act: -0.1700
Data Index: 3274755 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8032. Min Range: -1.8032
Max Act: 1.7601. Min Act: -0.1700
Data Index: 5994861 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8032. Min Range: -1.8032
Max Act: 1.7515. Min Act: -0.1700
Data Index: 3900344 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8032. Min Range: -1.8032
Max Act: 1.7601. Min Act: -0.1700
Data Index: 6995823 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8032. Min Range: -1.8032
Max Act: 1.7601. Min Act: -0.1699
Data Index: 7793044 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8032. Min Range: -1.8032
Max Act: 1.7601. Min Act: -0.1700
Data Index: 1470273 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8032. Min Range: -1.8032
Max Act: 1.7601. Min Act: -0.1699
Data Index: 3941654 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8032. Min Range: -1.8032
Max Act: 1.7515. Min Act: -0.1700
Data Index: 2384541 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8032. Min Range: -1.8032
Max Act: 1.7428. Min Act: -0.1694
Data Index: 3293997 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8032. Min Range: -1.8032
Max Act: 1.7342. Min Act: -0.1700
Data Index: 6859349 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8032. Min Range: -1.8032
Max Act: 1.7342. Min Act: -0.1698
Data Index: 8293559 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8032. Min Range: -1.8032
Max Act: 1.7428. Min Act: -0.1700
Data Index: 4302306 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8032. Min Range: -1.8032
Max Act: 1.7428. Min Act: -0.1700
Data Index: 2022357 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8032. Min Range: -1.8032
Max Act: 1.7428. Min Act: -0.1699
Data Index: 7599572 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8032. Min Range: -1.8032
Max Act: 1.7342. Min Act: -0.1700
Data Index: 5846186 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8032. Min Range: -1.8032
Max Act: 1.7428. Min Act: -0.1700
Data Index: 884555 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8032. Min Range: -1.8032
Max Act: 1.7342. Min Act: -0.1684
Data Index: 3587343 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8032. Min Range: -1.8032
Max Act: 1.7342. Min Act: -0.1700
Data Index: 2936369 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19