Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4550 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5885. Min Range: -5.5885
Max Act: 5.5885. Min Act: -0.1700
Data Index: 2253853 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5885. Min Range: -5.5885
Max Act: 5.5260. Min Act: -0.1700
Data Index: 8574540 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5885. Min Range: -5.5885
Max Act: 5.4948. Min Act: -0.1700
Data Index: 7869446 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5885. Min Range: -5.5885
Max Act: 5.4323. Min Act: -0.1700
Data Index: 280090 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5885. Min Range: -5.5885
Max Act: 5.3073. Min Act: -0.1700
Data Index: 1715028 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5885. Min Range: -5.5885
Max Act: 5.3073. Min Act: -0.1700
Data Index: 5024533 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5885. Min Range: -5.5885
Max Act: 5.3385. Min Act: -0.1700
Data Index: 5335131 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5885. Min Range: -5.5885
Max Act: 5.2760. Min Act: -0.1700
Data Index: 466208 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5885. Min Range: -5.5885
Max Act: 5.2448. Min Act: -0.1700
Data Index: 5030006 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5885. Min Range: -5.5885
Max Act: 5.2448. Min Act: -0.1700
Data Index: 334278 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5885. Min Range: -5.5885
Max Act: 5.2448. Min Act: -0.1700
Data Index: 6381871 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5885. Min Range: -5.5885
Max Act: 5.2135. Min Act: -0.1700
Data Index: 5367224 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5885. Min Range: -5.5885
Max Act: 5.1823. Min Act: -0.1700
Data Index: 3724018 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5885. Min Range: -5.5885
Max Act: 5.1510. Min Act: -0.1700
Data Index: 8621171 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5885. Min Range: -5.5885
Max Act: 5.1823. Min Act: -0.1700
Data Index: 4601223 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5885. Min Range: -5.5885
Max Act: 5.1823. Min Act: -0.1700
Data Index: 5229692 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5885. Min Range: -5.5885
Max Act: 5.0885. Min Act: -0.1700
Data Index: 8469893 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5885. Min Range: -5.5885
Max Act: 5.0885. Min Act: -0.1700
Data Index: 8087943 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5885. Min Range: -5.5885
Max Act: 5.1198. Min Act: -0.1700
Data Index: 334277 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5885. Min Range: -5.5885
Max Act: 5.1198. Min Act: -0.1700
Data Index: 3316138 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19