Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2498 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3819. Min Range: -5.3819
Max Act: 5.3506. Min Act: -0.1700
Data Index: 2633344 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3819. Min Range: -5.3819
Max Act: 5.3819. Min Act: -0.1700
Data Index: 1948020 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3819. Min Range: -5.3819
Max Act: 5.0381. Min Act: -0.1700
Data Index: 5203082 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3819. Min Range: -5.3819
Max Act: 4.9756. Min Act: -0.1700
Data Index: 3965539 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3819. Min Range: -5.3819
Max Act: 4.9131. Min Act: -0.1700
Data Index: 1696359 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3819. Min Range: -5.3819
Max Act: 4.9444. Min Act: -0.1700
Data Index: 711598 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3819. Min Range: -5.3819
Max Act: 4.9756. Min Act: -0.1700
Data Index: 6104400 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3819. Min Range: -5.3819
Max Act: 4.9131. Min Act: -0.1700
Data Index: 830682 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3819. Min Range: -5.3819
Max Act: 4.8819. Min Act: -0.1700
Data Index: 4975003 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3819. Min Range: -5.3819
Max Act: 4.9131. Min Act: -0.1700
Data Index: 1588228 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3819. Min Range: -5.3819
Max Act: 4.9444. Min Act: -0.1700
Data Index: 4583342 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3819. Min Range: -5.3819
Max Act: 4.9131. Min Act: -0.1700
Data Index: 8230010 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3819. Min Range: -5.3819
Max Act: 4.9131. Min Act: -0.1700
Data Index: 7871257 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3819. Min Range: -5.3819
Max Act: 4.8819. Min Act: -0.1700
Data Index: 7294393 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3819. Min Range: -5.3819
Max Act: 4.8819. Min Act: -0.1700
Data Index: 1775799 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3819. Min Range: -5.3819
Max Act: 4.8819. Min Act: -0.1700
Data Index: 3906033 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3819. Min Range: -5.3819
Max Act: 4.8819. Min Act: -0.1700
Data Index: 394332 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3819. Min Range: -5.3819
Max Act: 4.9131. Min Act: -0.1700
Data Index: 1779467 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3819. Min Range: -5.3819
Max Act: 4.8506. Min Act: -0.1700
Data Index: 2124349 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3819. Min Range: -5.3819
Max Act: 4.8506. Min Act: -0.1700
Data Index: 4755464 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19