Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3781 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4188. Min Range: -3.4188
Max Act: 3.4188. Min Act: -0.1700
Data Index: 2950213 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4188. Min Range: -3.4188
Max Act: 3.3403. Min Act: -0.1700
Data Index: 1183478 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4188. Min Range: -3.4188
Max Act: 3.3090. Min Act: -0.1700
Data Index: 3953163 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4188. Min Range: -3.4188
Max Act: 3.2776. Min Act: -0.1700
Data Index: 7803314 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4188. Min Range: -3.4188
Max Act: 3.2776. Min Act: -0.1700
Data Index: 3953162 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4188. Min Range: -3.4188
Max Act: 3.2776. Min Act: -0.1700
Data Index: 8378622 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4188. Min Range: -3.4188
Max Act: 3.2776. Min Act: -0.1700
Data Index: 1363916 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4188. Min Range: -3.4188
Max Act: 3.2618. Min Act: -0.1700
Data Index: 4791775 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4188. Min Range: -3.4188
Max Act: 3.2147. Min Act: -0.1700
Data Index: 2709641 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4188. Min Range: -3.4188
Max Act: 3.1990. Min Act: -0.1700
Data Index: 5212966 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4188. Min Range: -3.4188
Max Act: 3.1833. Min Act: -0.1700
Data Index: 6420778 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4188. Min Range: -3.4188
Max Act: 3.1990. Min Act: -0.1700
Data Index: 2259287 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4188. Min Range: -3.4188
Max Act: 3.1990. Min Act: -0.1700
Data Index: 6510737 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4188. Min Range: -3.4188
Max Act: 3.1833. Min Act: -0.1700
Data Index: 3816482 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4188. Min Range: -3.4188
Max Act: 3.1833. Min Act: -0.1700
Data Index: 3217571 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4188. Min Range: -3.4188
Max Act: 3.1360. Min Act: -0.1700
Data Index: 7878850 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4188. Min Range: -3.4188
Max Act: 3.1360. Min Act: -0.1700
Data Index: 982598 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4188. Min Range: -3.4188
Max Act: 3.1045. Min Act: -0.1700
Data Index: 3990540 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4188. Min Range: -3.4188
Max Act: 3.1360. Min Act: -0.1700
Data Index: 4555768 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4188. Min Range: -3.4188
Max Act: 3.1203. Min Act: -0.1700
Data Index: 7067157 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19