Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2494 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8459. Min Range: -3.8459
Max Act: 3.8459. Min Act: -0.1700
Data Index: 1445393 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8459. Min Range: -3.8459
Max Act: 3.7834. Min Act: -0.1700
Data Index: 7018195 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8459. Min Range: -3.8459
Max Act: 3.7521. Min Act: -0.1700
Data Index: 8443051 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8459. Min Range: -3.8459
Max Act: 3.7834. Min Act: -0.1700
Data Index: 429537 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8459. Min Range: -3.8459
Max Act: 3.8146. Min Act: -0.1700
Data Index: 3711437 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8459. Min Range: -3.8459
Max Act: 3.7208. Min Act: -0.1700
Data Index: 7635400 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8459. Min Range: -3.8459
Max Act: 3.7521. Min Act: -0.1700
Data Index: 839190 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8459. Min Range: -3.8459
Max Act: 3.8146. Min Act: -0.1700
Data Index: 6705533 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8459. Min Range: -3.8459
Max Act: 3.7208. Min Act: -0.1700
Data Index: 1491011 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8459. Min Range: -3.8459
Max Act: 3.7834. Min Act: -0.1700
Data Index: 5037827 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8459. Min Range: -3.8459
Max Act: 3.7208. Min Act: -0.1700
Data Index: 3306111 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8459. Min Range: -3.8459
Max Act: 3.6895. Min Act: -0.1700
Data Index: 5868777 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8459. Min Range: -3.8459
Max Act: 3.7834. Min Act: -0.1700
Data Index: 3270678 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8459. Min Range: -3.8459
Max Act: 3.8146. Min Act: -0.1700
Data Index: 1387914 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8459. Min Range: -3.8459
Max Act: 3.6895. Min Act: -0.1700
Data Index: 5624536 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8459. Min Range: -3.8459
Max Act: 3.7521. Min Act: -0.1700
Data Index: 2986604 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8459. Min Range: -3.8459
Max Act: 3.7208. Min Act: -0.1700
Data Index: 4865270 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8459. Min Range: -3.8459
Max Act: 3.6269. Min Act: -0.1700
Data Index: 1298753 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8459. Min Range: -3.8459
Max Act: 3.6895. Min Act: -0.1700
Data Index: 4427248 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8459. Min Range: -3.8459
Max Act: 3.7521. Min Act: -0.1700
Data Index: 4123473 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19