Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2481 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2454. Min Range: -6.2454
Max Act: 6.2454. Min Act: -0.1700
Data Index: 2113132 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.9016. Min Act: -0.1700
Data Index: 8189881 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.8391. Min Act: -0.1700
Data Index: 6816550 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.8079. Min Act: -0.1700
Data Index: 6531641 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.7141. Min Act: -0.1700
Data Index: 1210435 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.7141. Min Act: -0.1700
Data Index: 5102073 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.6829. Min Act: -0.1700
Data Index: 1064426 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.6829. Min Act: -0.1700
Data Index: 5592290 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.7141. Min Act: -0.1700
Data Index: 7096394 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.6516. Min Act: -0.1700
Data Index: 8028372 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.6516. Min Act: -0.1700
Data Index: 8050172 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.6204. Min Act: -0.1700
Data Index: 3107716 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.6204. Min Act: -0.1700
Data Index: 3798911 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.6204. Min Act: -0.1700
Data Index: 6046072 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.5891. Min Act: -0.1700
Data Index: 4517323 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.6204. Min Act: -0.1700
Data Index: 4924080 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.5891. Min Act: -0.1700
Data Index: 5853873 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.5579. Min Act: -0.1700
Data Index: 2760026 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.5579. Min Act: -0.1700
Data Index: 3851960 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.5579. Min Act: -0.1700
Data Index: 2661077 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19