Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2528 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4234. Min Range: -4.4234
Max Act: 4.4234. Min Act: -0.1700
Data Index: 3410724 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4234. Min Range: -4.4234
Max Act: 4.4234. Min Act: -0.1700
Data Index: 2503303 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4234. Min Range: -4.4234
Max Act: 4.3297. Min Act: -0.1700
Data Index: 6302545 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4234. Min Range: -4.4234
Max Act: 4.2672. Min Act: -0.1700
Data Index: 5755324 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4234. Min Range: -4.4234
Max Act: 4.2672. Min Act: -0.1700
Data Index: 1270373 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4234. Min Range: -4.4234
Max Act: 4.2047. Min Act: -0.1700
Data Index: 1840096 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4234. Min Range: -4.4234
Max Act: 4.2047. Min Act: -0.1700
Data Index: 2291946 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4234. Min Range: -4.4234
Max Act: 4.1734. Min Act: -0.1700
Data Index: 2980020 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4234. Min Range: -4.4234
Max Act: 4.1734. Min Act: -0.1700
Data Index: 2641064 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4234. Min Range: -4.4234
Max Act: 4.1734. Min Act: -0.1700
Data Index: 21466 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4234. Min Range: -4.4234
Max Act: 4.1734. Min Act: -0.1700
Data Index: 1690431 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4234. Min Range: -4.4234
Max Act: 4.1422. Min Act: -0.1700
Data Index: 3141741 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4234. Min Range: -4.4234
Max Act: 4.1422. Min Act: -0.1700
Data Index: 6378988 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4234. Min Range: -4.4234
Max Act: 4.1422. Min Act: -0.1700
Data Index: 1685084 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4234. Min Range: -4.4234
Max Act: 4.1422. Min Act: -0.1700
Data Index: 4286186 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4234. Min Range: -4.4234
Max Act: 4.1109. Min Act: -0.1700
Data Index: 1231391 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4234. Min Range: -4.4234
Max Act: 4.1109. Min Act: -0.1700
Data Index: 6094577 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4234. Min Range: -4.4234
Max Act: 4.0796. Min Act: -0.1700
Data Index: 5495145 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4234. Min Range: -4.4234
Max Act: 4.0796. Min Act: -0.1700
Data Index: 1541125 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4234. Min Range: -4.4234
Max Act: 4.0796. Min Act: -0.1700
Data Index: 6888580 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19