Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 98 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3648. Min Range: -8.3648
Max Act: 8.3648. Min Act: -0.1700
Data Index: 2806380 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3648. Min Range: -8.3648
Max Act: 8.1773. Min Act: -0.1700
Data Index: 4096298 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3648. Min Range: -8.3648
Max Act: 8.1460. Min Act: -0.1700
Data Index: 2508466 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3648. Min Range: -8.3648
Max Act: 8.0835. Min Act: -0.1700
Data Index: 6365605 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3648. Min Range: -8.3648
Max Act: 8.0835. Min Act: -0.1700
Data Index: 6517751 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3648. Min Range: -8.3648
Max Act: 8.0835. Min Act: -0.1700
Data Index: 259225 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3648. Min Range: -8.3648
Max Act: 8.0835. Min Act: -0.1700
Data Index: 5408305 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3648. Min Range: -8.3648
Max Act: 8.0210. Min Act: -0.1700
Data Index: 8300955 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3648. Min Range: -8.3648
Max Act: 8.0523. Min Act: -0.1700
Data Index: 5805348 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3648. Min Range: -8.3648
Max Act: 8.0835. Min Act: -0.1700
Data Index: 7983405 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3648. Min Range: -8.3648
Max Act: 8.0523. Min Act: -0.1700
Data Index: 8093550 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3648. Min Range: -8.3648
Max Act: 8.0210. Min Act: -0.1700
Data Index: 2269065 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3648. Min Range: -8.3648
Max Act: 8.0210. Min Act: -0.1700
Data Index: 5907060 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3648. Min Range: -8.3648
Max Act: 8.0210. Min Act: -0.1700
Data Index: 8635705 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3648. Min Range: -8.3648
Max Act: 7.9898. Min Act: -0.1700
Data Index: 5722007 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3648. Min Range: -8.3648
Max Act: 7.9273. Min Act: -0.1700
Data Index: 7482945 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3648. Min Range: -8.3648
Max Act: 7.9898. Min Act: -0.1700
Data Index: 4210591 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3648. Min Range: -8.3648
Max Act: 7.9273. Min Act: -0.1700
Data Index: 2283046 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3648. Min Range: -8.3648
Max Act: 7.9585. Min Act: -0.1700
Data Index: 7190698 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3648. Min Range: -8.3648
Max Act: 7.9585. Min Act: -0.1700
Data Index: 3614386 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19