Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2079 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3110. Min Range: -8.3110
Max Act: 8.3110. Min Act: -0.1700
Data Index: 4457628 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3110. Min Range: -8.3110
Max Act: 8.0610. Min Act: -0.1700
Data Index: 1490177 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3110. Min Range: -8.3110
Max Act: 7.9047. Min Act: -0.1700
Data Index: 7869893 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3110. Min Range: -8.3110
Max Act: 7.7797. Min Act: -0.1700
Data Index: 6157979 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3110. Min Range: -8.3110
Max Act: 7.7485. Min Act: -0.1700
Data Index: 3634298 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3110. Min Range: -8.3110
Max Act: 7.6860. Min Act: -0.1700
Data Index: 2887825 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3110. Min Range: -8.3110
Max Act: 7.6860. Min Act: -0.1700
Data Index: 3313801 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3110. Min Range: -8.3110
Max Act: 7.6860. Min Act: -0.1700
Data Index: 4191512 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3110. Min Range: -8.3110
Max Act: 7.6860. Min Act: -0.1700
Data Index: 1449069 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3110. Min Range: -8.3110
Max Act: 7.6860. Min Act: -0.1700
Data Index: 313722 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3110. Min Range: -8.3110
Max Act: 7.6547. Min Act: -0.1700
Data Index: 4096842 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3110. Min Range: -8.3110
Max Act: 7.6547. Min Act: -0.1700
Data Index: 5848290 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3110. Min Range: -8.3110
Max Act: 7.6547. Min Act: -0.1700
Data Index: 3347263 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3110. Min Range: -8.3110
Max Act: 7.6235. Min Act: -0.1700
Data Index: 3108072 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3110. Min Range: -8.3110
Max Act: 7.6235. Min Act: -0.1700
Data Index: 4930869 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3110. Min Range: -8.3110
Max Act: 7.5922. Min Act: -0.1700
Data Index: 3171137 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3110. Min Range: -8.3110
Max Act: 7.5610. Min Act: -0.1700
Data Index: 3021080 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3110. Min Range: -8.3110
Max Act: 7.5610. Min Act: -0.1700
Data Index: 1263782 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3110. Min Range: -8.3110
Max Act: 7.5610. Min Act: -0.1700
Data Index: 708266 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3110. Min Range: -8.3110
Max Act: 7.5610. Min Act: -0.1700
Data Index: 5629425 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #19