Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2080 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2244. Min Range: -5.2244
Max Act: 5.2244. Min Act: -0.1700
Data Index: 3534941 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2244. Min Range: -5.2244
Max Act: 5.1619. Min Act: -0.1700
Data Index: 8078265 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2244. Min Range: -5.2244
Max Act: 5.1306. Min Act: -0.1700
Data Index: 5748967 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2244. Min Range: -5.2244
Max Act: 5.0994. Min Act: -0.1700
Data Index: 5053878 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2244. Min Range: -5.2244
Max Act: 5.0681. Min Act: -0.1700
Data Index: 7239038 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2244. Min Range: -5.2244
Max Act: 5.0369. Min Act: -0.1700
Data Index: 884494 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2244. Min Range: -5.2244
Max Act: 5.0056. Min Act: -0.1700
Data Index: 6430771 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2244. Min Range: -5.2244
Max Act: 5.0369. Min Act: -0.1700
Data Index: 1982923 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2244. Min Range: -5.2244
Max Act: 4.9744. Min Act: -0.1700
Data Index: 3453104 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2244. Min Range: -5.2244
Max Act: 5.0056. Min Act: -0.1700
Data Index: 6905543 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2244. Min Range: -5.2244
Max Act: 4.9744. Min Act: -0.1700
Data Index: 3678437 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2244. Min Range: -5.2244
Max Act: 4.9119. Min Act: -0.1700
Data Index: 5672380 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2244. Min Range: -5.2244
Max Act: 4.9431. Min Act: -0.1700
Data Index: 8753556 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2244. Min Range: -5.2244
Max Act: 4.9431. Min Act: -0.1700
Data Index: 3155874 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2244. Min Range: -5.2244
Max Act: 4.9431. Min Act: -0.1700
Data Index: 4215713 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2244. Min Range: -5.2244
Max Act: 4.9431. Min Act: -0.1700
Data Index: 1884454 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2244. Min Range: -5.2244
Max Act: 4.9431. Min Act: -0.1700
Data Index: 5434509 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2244. Min Range: -5.2244
Max Act: 4.9119. Min Act: -0.1700
Data Index: 3156186 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2244. Min Range: -5.2244
Max Act: 4.8494. Min Act: -0.1700
Data Index: 23096 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2244. Min Range: -5.2244
Max Act: 4.8806. Min Act: -0.1700
Data Index: 4527101 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19