Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4029 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1512. Min Range: -2.1512
Max Act: 2.1345. Min Act: -0.1700
Data Index: 1246604 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1512. Min Range: -2.1512
Max Act: 2.1345. Min Act: -0.1700
Data Index: 4027256 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1512. Min Range: -2.1512
Max Act: 2.1512. Min Act: -0.1700
Data Index: 8287808 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1512. Min Range: -2.1512
Max Act: 2.1178. Min Act: -0.1700
Data Index: 801797 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1512. Min Range: -2.1512
Max Act: 2.1178. Min Act: -0.1700
Data Index: 6984797 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1512. Min Range: -2.1512
Max Act: 2.0843. Min Act: -0.1700
Data Index: 988107 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1512. Min Range: -2.1512
Max Act: 2.1011. Min Act: -0.1700
Data Index: 5022532 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1512. Min Range: -2.1512
Max Act: 2.0843. Min Act: -0.1700
Data Index: 4840488 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1512. Min Range: -2.1512
Max Act: 2.0675. Min Act: -0.1700
Data Index: 368733 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1512. Min Range: -2.1512
Max Act: 2.0675. Min Act: -0.1700
Data Index: 5351581 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1512. Min Range: -2.1512
Max Act: 2.0170. Min Act: -0.1700
Data Index: 1849576 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1512. Min Range: -2.1512
Max Act: 2.0339. Min Act: -0.1700
Data Index: 1216265 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1512. Min Range: -2.1512
Max Act: 2.0339. Min Act: -0.1700
Data Index: 3245978 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1512. Min Range: -2.1512
Max Act: 2.0339. Min Act: -0.1699
Data Index: 1959075 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1512. Min Range: -2.1512
Max Act: 2.0170. Min Act: -0.1700
Data Index: 1561189 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1512. Min Range: -2.1512
Max Act: 2.0507. Min Act: -0.1700
Data Index: 3071520 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1512. Min Range: -2.1512
Max Act: 2.0001. Min Act: -0.1700
Data Index: 7123965 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1512. Min Range: -2.1512
Max Act: 2.0170. Min Act: -0.1700
Data Index: 7368565 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1512. Min Range: -2.1512
Max Act: 2.0001. Min Act: -0.1700
Data Index: 3336302 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1512. Min Range: -2.1512
Max Act: 2.0001. Min Act: -0.1700
Data Index: 177269 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #19