Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3678 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.9332. Min Act: -0.1700
Data Index: 36340 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.9332. Min Act: -0.1700
Data Index: 3578185 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.9332. Min Act: -0.1700
Data Index: 5941665 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.9019. Min Act: -0.1700
Data Index: 4760320 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.8707. Min Act: -0.1700
Data Index: 614413 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.8707. Min Act: -0.1700
Data Index: 6438509 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.8394. Min Act: -0.1700
Data Index: 3334511 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.8707. Min Act: -0.1700
Data Index: 7569459 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.8394. Min Act: -0.1700
Data Index: 7569460 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.8394. Min Act: -0.1700
Data Index: 894382 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.8394. Min Act: -0.1700
Data Index: 3149624 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.8394. Min Act: -0.1700
Data Index: 1170645 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.8394. Min Act: -0.1700
Data Index: 8716476 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.8394. Min Act: -0.1700
Data Index: 8781019 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.8394. Min Act: -0.1700
Data Index: 3111129 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.8082. Min Act: -0.1700
Data Index: 8245534 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.8082. Min Act: -0.1700
Data Index: 2567702 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.8082. Min Act: -0.1700
Data Index: 5705845 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.8082. Min Act: -0.1700
Data Index: 2497027 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.8082. Min Act: -0.1700
Data Index: 7128647 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19