Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3403 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9108. Min Range: -4.9108
Max Act: 4.9108. Min Act: -0.1700
Data Index: 2603083 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9108. Min Range: -4.9108
Max Act: 4.7545. Min Act: -0.1700
Data Index: 2305694 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9108. Min Range: -4.9108
Max Act: 4.7545. Min Act: -0.1700
Data Index: 1962527 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9108. Min Range: -4.9108
Max Act: 4.7233. Min Act: -0.1700
Data Index: 3613456 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9108. Min Range: -4.9108
Max Act: 4.7233. Min Act: -0.1700
Data Index: 1591852 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9108. Min Range: -4.9108
Max Act: 4.6920. Min Act: -0.1700
Data Index: 959556 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9108. Min Range: -4.9108
Max Act: 4.6608. Min Act: -0.1700
Data Index: 5506543 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9108. Min Range: -4.9108
Max Act: 4.6608. Min Act: -0.1700
Data Index: 3265484 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9108. Min Range: -4.9108
Max Act: 4.6295. Min Act: -0.1700
Data Index: 1569285 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9108. Min Range: -4.9108
Max Act: 4.6295. Min Act: -0.1700
Data Index: 961537 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9108. Min Range: -4.9108
Max Act: 4.6295. Min Act: -0.1700
Data Index: 2924248 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9108. Min Range: -4.9108
Max Act: 4.6608. Min Act: -0.1700
Data Index: 5394609 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9108. Min Range: -4.9108
Max Act: 4.5983. Min Act: -0.1700
Data Index: 1758549 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9108. Min Range: -4.9108
Max Act: 4.5983. Min Act: -0.1700
Data Index: 2709627 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9108. Min Range: -4.9108
Max Act: 4.5983. Min Act: -0.1700
Data Index: 705299 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9108. Min Range: -4.9108
Max Act: 4.5670. Min Act: -0.1700
Data Index: 1860722 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9108. Min Range: -4.9108
Max Act: 4.5670. Min Act: -0.1700
Data Index: 2656226 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9108. Min Range: -4.9108
Max Act: 4.5358. Min Act: -0.1700
Data Index: 3758190 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9108. Min Range: -4.9108
Max Act: 4.5670. Min Act: -0.1700
Data Index: 2715471 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9108. Min Range: -4.9108
Max Act: 4.5358. Min Act: -0.1700
Data Index: 4370128 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19