Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1931 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9846. Min Range: -6.9846
Max Act: 6.9846. Min Act: -0.1700
Data Index: 4358941 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9846. Min Range: -6.9846
Max Act: 6.5783. Min Act: -0.1700
Data Index: 515879 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9846. Min Range: -6.9846
Max Act: 6.6096. Min Act: -0.1700
Data Index: 7803563 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9846. Min Range: -6.9846
Max Act: 6.6096. Min Act: -0.1700
Data Index: 5831370 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9846. Min Range: -6.9846
Max Act: 6.5158. Min Act: -0.1700
Data Index: 1060506 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9846. Min Range: -6.9846
Max Act: 6.4533. Min Act: -0.1700
Data Index: 1328264 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9846. Min Range: -6.9846
Max Act: 6.4846. Min Act: -0.1700
Data Index: 8161306 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9846. Min Range: -6.9846
Max Act: 6.4533. Min Act: -0.1700
Data Index: 2428587 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9846. Min Range: -6.9846
Max Act: 6.3596. Min Act: -0.1700
Data Index: 7827758 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9846. Min Range: -6.9846
Max Act: 6.3283. Min Act: -0.1700
Data Index: 4401808 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9846. Min Range: -6.9846
Max Act: 6.3283. Min Act: -0.1700
Data Index: 5358258 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9846. Min Range: -6.9846
Max Act: 6.2971. Min Act: -0.1700
Data Index: 6922181 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9846. Min Range: -6.9846
Max Act: 6.2971. Min Act: -0.1700
Data Index: 5577834 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9846. Min Range: -6.9846
Max Act: 6.2658. Min Act: -0.1700
Data Index: 140811 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9846. Min Range: -6.9846
Max Act: 6.2658. Min Act: -0.1700
Data Index: 2721129 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9846. Min Range: -6.9846
Max Act: 6.2658. Min Act: -0.1700
Data Index: 163376 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9846. Min Range: -6.9846
Max Act: 6.2346. Min Act: -0.1700
Data Index: 284656 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9846. Min Range: -6.9846
Max Act: 6.2346. Min Act: -0.1700
Data Index: 5386630 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9846. Min Range: -6.9846
Max Act: 6.2033. Min Act: -0.1700
Data Index: 5187176 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9846. Min Range: -6.9846
Max Act: 6.1721. Min Act: -0.1700
Data Index: 6633772 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #19