Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2722 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.9463. Min Act: -0.1700
Data Index: 4255553 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.9151. Min Act: -0.1700
Data Index: 5850923 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.8838. Min Act: -0.1700
Data Index: 7129637 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.8838. Min Act: -0.1700
Data Index: 1602486 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.7901. Min Act: -0.1700
Data Index: 92282 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.7901. Min Act: -0.1700
Data Index: 1418735 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.7276. Min Act: -0.1700
Data Index: 7349369 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.6963. Min Act: -0.1700
Data Index: 1695927 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.6963. Min Act: -0.1700
Data Index: 3871894 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.6651. Min Act: -0.1700
Data Index: 4884768 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.6338. Min Act: -0.1700
Data Index: 7250160 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.6338. Min Act: -0.1700
Data Index: 217838 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.6338. Min Act: -0.1700
Data Index: 4242499 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.5713. Min Act: -0.1700
Data Index: 6561953 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.5713. Min Act: -0.1700
Data Index: 7658690 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.5401. Min Act: -0.1700
Data Index: 5717363 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.5713. Min Act: -0.1700
Data Index: 7036621 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.5401. Min Act: -0.1700
Data Index: 531532 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.5088. Min Act: -0.1700
Data Index: 6610244 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.5088. Min Act: -0.1700
Data Index: 7531201 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19