Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3535 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2188. Min Range: -7.2188
Max Act: 7.2188. Min Act: -0.1700
Data Index: 418702 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2188. Min Range: -7.2188
Max Act: 7.0313. Min Act: -0.1700
Data Index: 1219786 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.9688. Min Act: -0.1700
Data Index: 7913374 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.9688. Min Act: -0.1700
Data Index: 7984166 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.9063. Min Act: -0.1700
Data Index: 4094050 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.8751. Min Act: -0.1700
Data Index: 3213934 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.8438. Min Act: -0.1700
Data Index: 6751228 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.8438. Min Act: -0.1700
Data Index: 7580852 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.8126. Min Act: -0.1700
Data Index: 121480 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.8126. Min Act: -0.1700
Data Index: 944333 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.7501. Min Act: -0.1700
Data Index: 2809383 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.7188. Min Act: -0.1700
Data Index: 15448 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.7501. Min Act: -0.1700
Data Index: 6133863 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.7188. Min Act: -0.1700
Data Index: 2207792 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.7188. Min Act: -0.1700
Data Index: 5406504 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.7188. Min Act: -0.1700
Data Index: 953247 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.7188. Min Act: -0.1700
Data Index: 8623790 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.6876. Min Act: -0.1700
Data Index: 3379130 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.6876. Min Act: -0.1700
Data Index: 5316312 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.6876. Min Act: -0.1700
Data Index: 8653337 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19