Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3446 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2450. Min Range: -6.2450
Max Act: 6.2450. Min Act: -0.1700
Data Index: 2102089 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2450. Min Range: -6.2450
Max Act: 5.9637. Min Act: -0.1700
Data Index: 5127063 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2450. Min Range: -6.2450
Max Act: 5.9012. Min Act: -0.1700
Data Index: 4651107 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2450. Min Range: -6.2450
Max Act: 5.9012. Min Act: -0.1700
Data Index: 6563342 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2450. Min Range: -6.2450
Max Act: 5.8700. Min Act: -0.1700
Data Index: 522749 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2450. Min Range: -6.2450
Max Act: 5.8387. Min Act: -0.1700
Data Index: 2963463 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2450. Min Range: -6.2450
Max Act: 5.7450. Min Act: -0.1700
Data Index: 2118670 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2450. Min Range: -6.2450
Max Act: 5.7450. Min Act: -0.1700
Data Index: 674156 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2450. Min Range: -6.2450
Max Act: 5.7762. Min Act: -0.1700
Data Index: 3702134 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2450. Min Range: -6.2450
Max Act: 5.7450. Min Act: -0.1700
Data Index: 8344009 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2450. Min Range: -6.2450
Max Act: 5.7137. Min Act: -0.1700
Data Index: 6301887 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2450. Min Range: -6.2450
Max Act: 5.7137. Min Act: -0.1700
Data Index: 1506807 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2450. Min Range: -6.2450
Max Act: 5.6825. Min Act: -0.1700
Data Index: 6207066 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2450. Min Range: -6.2450
Max Act: 5.6825. Min Act: -0.1700
Data Index: 7841100 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2450. Min Range: -6.2450
Max Act: 5.6825. Min Act: -0.1700
Data Index: 757468 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2450. Min Range: -6.2450
Max Act: 5.6512. Min Act: -0.1700
Data Index: 1925911 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2450. Min Range: -6.2450
Max Act: 5.6200. Min Act: -0.1700
Data Index: 15169 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2450. Min Range: -6.2450
Max Act: 5.6200. Min Act: -0.1700
Data Index: 4903984 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2450. Min Range: -6.2450
Max Act: 5.6200. Min Act: -0.1700
Data Index: 4788137 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2450. Min Range: -6.2450
Max Act: 5.6200. Min Act: -0.1700
Data Index: 2594124 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19