Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1050 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7399. Min Range: -8.7399
Max Act: 8.7399. Min Act: -0.1700
Data Index: 3979219 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7399. Min Range: -8.7399
Max Act: 8.3336. Min Act: -0.1700
Data Index: 3979501 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7399. Min Range: -8.7399
Max Act: 8.3336. Min Act: -0.1700
Data Index: 7718731 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7399. Min Range: -8.7399
Max Act: 8.1774. Min Act: -0.1700
Data Index: 3979220 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7399. Min Range: -8.7399
Max Act: 8.0836. Min Act: -0.1700
Data Index: 627816 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7399. Min Range: -8.7399
Max Act: 8.0524. Min Act: -0.1700
Data Index: 7145716 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7399. Min Range: -8.7399
Max Act: 7.9899. Min Act: -0.1700
Data Index: 7729931 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7399. Min Range: -8.7399
Max Act: 7.9586. Min Act: -0.1700
Data Index: 1447436 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7399. Min Range: -8.7399
Max Act: 7.9899. Min Act: -0.1700
Data Index: 7348791 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7399. Min Range: -8.7399
Max Act: 7.8961. Min Act: -0.1700
Data Index: 2464567 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7399. Min Range: -8.7399
Max Act: 7.8961. Min Act: -0.1700
Data Index: 8522610 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7399. Min Range: -8.7399
Max Act: 7.8961. Min Act: -0.1700
Data Index: 8004593 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7399. Min Range: -8.7399
Max Act: 7.8336. Min Act: -0.1700
Data Index: 5354112 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7399. Min Range: -8.7399
Max Act: 7.8336. Min Act: -0.1700
Data Index: 7116206 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7399. Min Range: -8.7399
Max Act: 7.8336. Min Act: -0.1700
Data Index: 4565811 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7399. Min Range: -8.7399
Max Act: 7.8336. Min Act: -0.1700
Data Index: 4152516 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7399. Min Range: -8.7399
Max Act: 7.8024. Min Act: -0.1700
Data Index: 6978204 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7399. Min Range: -8.7399
Max Act: 7.8024. Min Act: -0.1700
Data Index: 4964637 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7399. Min Range: -8.7399
Max Act: 7.8024. Min Act: -0.1700
Data Index: 597270 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7399. Min Range: -8.7399
Max Act: 7.8024. Min Act: -0.1700
Data Index: 2101838 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #19