Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 44 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.4644. Min Range: -9.4644
Max Act: 9.4644. Min Act: -0.1700
Data Index: 3734123 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4644. Min Range: -9.4644
Max Act: 9.4644. Min Act: -0.1700
Data Index: 7251077 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4644. Min Range: -9.4644
Max Act: 9.4019. Min Act: -0.1700
Data Index: 6281361 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4644. Min Range: -9.4644
Max Act: 9.3394. Min Act: -0.1700
Data Index: 4055689 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4644. Min Range: -9.4644
Max Act: 9.4019. Min Act: -0.1700
Data Index: 1746154 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4644. Min Range: -9.4644
Max Act: 9.2769. Min Act: -0.1700
Data Index: 425387 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4644. Min Range: -9.4644
Max Act: 9.1519. Min Act: -0.1700
Data Index: 4701073 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4644. Min Range: -9.4644
Max Act: 9.1519. Min Act: -0.1700
Data Index: 4306545 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4644. Min Range: -9.4644
Max Act: 9.2769. Min Act: -0.1700
Data Index: 8790501 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4644. Min Range: -9.4644
Max Act: 9.1519. Min Act: -0.1700
Data Index: 2725073 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4644. Min Range: -9.4644
Max Act: 9.1519. Min Act: -0.1700
Data Index: 1810451 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4644. Min Range: -9.4644
Max Act: 9.1519. Min Act: -0.1700
Data Index: 2890574 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4644. Min Range: -9.4644
Max Act: 9.0894. Min Act: -0.1700
Data Index: 4651136 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4644. Min Range: -9.4644
Max Act: 9.0269. Min Act: -0.1700
Data Index: 5424317 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4644. Min Range: -9.4644
Max Act: 9.0269. Min Act: -0.1700
Data Index: 2650386 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4644. Min Range: -9.4644
Max Act: 9.0269. Min Act: -0.1700
Data Index: 1117713 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4644. Min Range: -9.4644
Max Act: 9.0269. Min Act: -0.1700
Data Index: 2653987 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4644. Min Range: -9.4644
Max Act: 8.9644. Min Act: -0.1700
Data Index: 2981067 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4644. Min Range: -9.4644
Max Act: 8.9644. Min Act: -0.1700
Data Index: 1467557 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4644. Min Range: -9.4644
Max Act: 8.9644. Min Act: -0.1700
Data Index: 271294 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19