Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2788 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3476. Min Range: -6.3476
Max Act: 6.3476. Min Act: -0.1700
Data Index: 1366728 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3476. Min Range: -6.3476
Max Act: 6.2851. Min Act: -0.1700
Data Index: 4056002 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3476. Min Range: -6.3476
Max Act: 6.2538. Min Act: -0.1700
Data Index: 134175 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3476. Min Range: -6.3476
Max Act: 6.1913. Min Act: -0.1700
Data Index: 5019023 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3476. Min Range: -6.3476
Max Act: 6.1288. Min Act: -0.1700
Data Index: 687572 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3476. Min Range: -6.3476
Max Act: 6.1288. Min Act: -0.1700
Data Index: 5192748 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3476. Min Range: -6.3476
Max Act: 6.1288. Min Act: -0.1700
Data Index: 6751882 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3476. Min Range: -6.3476
Max Act: 6.0976. Min Act: -0.1700
Data Index: 5193862 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3476. Min Range: -6.3476
Max Act: 6.0976. Min Act: -0.1700
Data Index: 4111578 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3476. Min Range: -6.3476
Max Act: 6.0038. Min Act: -0.1700
Data Index: 8071889 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3476. Min Range: -6.3476
Max Act: 5.9726. Min Act: -0.1700
Data Index: 5943471 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3476. Min Range: -6.3476
Max Act: 5.9413. Min Act: -0.1700
Data Index: 6338028 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3476. Min Range: -6.3476
Max Act: 5.9101. Min Act: -0.1700
Data Index: 1446318 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3476. Min Range: -6.3476
Max Act: 5.9726. Min Act: -0.1700
Data Index: 7905399 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3476. Min Range: -6.3476
Max Act: 5.8788. Min Act: -0.1700
Data Index: 4274975 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3476. Min Range: -6.3476
Max Act: 5.8163. Min Act: -0.1700
Data Index: 3466236 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3476. Min Range: -6.3476
Max Act: 5.8476. Min Act: -0.1700
Data Index: 5213553 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3476. Min Range: -6.3476
Max Act: 5.8163. Min Act: -0.1695
Data Index: 803353 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3476. Min Range: -6.3476
Max Act: 5.8163. Min Act: -0.1700
Data Index: 1386379 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3476. Min Range: -6.3476
Max Act: 5.7226. Min Act: -0.1700
Data Index: 3735719 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19