Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 276 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.5600. Min Act: -0.1700
Data Index: 2210913 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.5600. Min Act: -0.1700
Data Index: 6544927 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.4662. Min Act: -0.1700
Data Index: 1099945 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.4662. Min Act: -0.1700
Data Index: 1136891 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.4350. Min Act: -0.1700
Data Index: 7537131 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.4350. Min Act: -0.1700
Data Index: 7215227 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.4037. Min Act: -0.1700
Data Index: 2983289 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.3725. Min Act: -0.1700
Data Index: 2410447 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.3725. Min Act: -0.1700
Data Index: 1667991 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.3725. Min Act: -0.1700
Data Index: 2638975 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.3725. Min Act: -0.1700
Data Index: 568937 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.3412. Min Act: -0.1700
Data Index: 2364294 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.3100. Min Act: -0.1700
Data Index: 4313308 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.2787. Min Act: -0.1700
Data Index: 7948816 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.3412. Min Act: -0.1700
Data Index: 6245278 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.2787. Min Act: -0.1700
Data Index: 549949 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.2475. Min Act: -0.1700
Data Index: 4383177 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.2475. Min Act: -0.1700
Data Index: 2705886 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.2475. Min Act: -0.1700
Data Index: 8305114 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.2787. Min Act: -0.1699
Data Index: 4570076 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #19