Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1091 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9668. Min Range: -5.9668
Max Act: 5.9668. Min Act: -0.1700
Data Index: 3266314 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9668. Min Range: -5.9668
Max Act: 5.9043. Min Act: -0.1700
Data Index: 955151 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9668. Min Range: -5.9668
Max Act: 5.9043. Min Act: -0.1700
Data Index: 7618888 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9668. Min Range: -5.9668
Max Act: 5.8731. Min Act: -0.1700
Data Index: 3813422 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9668. Min Range: -5.9668
Max Act: 5.8731. Min Act: -0.1700
Data Index: 5709169 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9668. Min Range: -5.9668
Max Act: 5.8106. Min Act: -0.1700
Data Index: 6349203 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9668. Min Range: -5.9668
Max Act: 5.8106. Min Act: -0.1700
Data Index: 3953789 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9668. Min Range: -5.9668
Max Act: 5.7793. Min Act: -0.1700
Data Index: 3956449 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9668. Min Range: -5.9668
Max Act: 5.8106. Min Act: -0.1700
Data Index: 7339979 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9668. Min Range: -5.9668
Max Act: 5.8418. Min Act: -0.1700
Data Index: 2176549 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9668. Min Range: -5.9668
Max Act: 5.8106. Min Act: -0.1700
Data Index: 8617297 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9668. Min Range: -5.9668
Max Act: 5.7793. Min Act: -0.1700
Data Index: 6958822 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9668. Min Range: -5.9668
Max Act: 5.7793. Min Act: -0.1700
Data Index: 5795598 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9668. Min Range: -5.9668
Max Act: 5.7481. Min Act: -0.1700
Data Index: 8048177 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9668. Min Range: -5.9668
Max Act: 5.7793. Min Act: -0.1700
Data Index: 911763 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9668. Min Range: -5.9668
Max Act: 5.7793. Min Act: -0.1700
Data Index: 434125 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9668. Min Range: -5.9668
Max Act: 5.7793. Min Act: -0.1700
Data Index: 904025 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9668. Min Range: -5.9668
Max Act: 5.7793. Min Act: -0.1700
Data Index: 996593 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9668. Min Range: -5.9668
Max Act: 5.7793. Min Act: -0.1700
Data Index: 7108376 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9668. Min Range: -5.9668
Max Act: 5.7481. Min Act: -0.1700
Data Index: 1318949 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19