Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2704 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.7080. Min Act: -0.1700
Data Index: 5783188 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.5830. Min Act: -0.1700
Data Index: 5586272 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.5830. Min Act: -0.1700
Data Index: 10863 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.5517. Min Act: -0.1700
Data Index: 4441248 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.4580. Min Act: -0.1700
Data Index: 3779434 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.4267. Min Act: -0.1700
Data Index: 5335924 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.4267. Min Act: -0.1700
Data Index: 3779435 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.3955. Min Act: -0.1700
Data Index: 6090703 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.3955. Min Act: -0.1700
Data Index: 3105000 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.3642. Min Act: -0.1700
Data Index: 5722988 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.3330. Min Act: -0.1700
Data Index: 5202251 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.3330. Min Act: -0.1700
Data Index: 6950183 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.3330. Min Act: -0.1700
Data Index: 7225132 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.3330. Min Act: -0.1700
Data Index: 8435101 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.3017. Min Act: -0.1700
Data Index: 2757526 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.3017. Min Act: -0.1700
Data Index: 5081460 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.2705. Min Act: -0.1700
Data Index: 6442289 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.2705. Min Act: -0.1700
Data Index: 898555 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.2705. Min Act: -0.1700
Data Index: 3565612 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.2392. Min Act: -0.1700
Data Index: 8248373 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19