Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2702 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0273. Min Range: -7.0273
Max Act: 7.0273. Min Act: -0.1700
Data Index: 7191873 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0273. Min Range: -7.0273
Max Act: 6.8710. Min Act: -0.1700
Data Index: 3364509 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0273. Min Range: -7.0273
Max Act: 6.6523. Min Act: -0.1700
Data Index: 4812558 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0273. Min Range: -7.0273
Max Act: 6.5898. Min Act: -0.1700
Data Index: 789878 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0273. Min Range: -7.0273
Max Act: 6.6210. Min Act: -0.1700
Data Index: 593055 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0273. Min Range: -7.0273
Max Act: 6.5585. Min Act: -0.1700
Data Index: 5068103 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0273. Min Range: -7.0273
Max Act: 6.5585. Min Act: -0.1700
Data Index: 3640207 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0273. Min Range: -7.0273
Max Act: 6.5585. Min Act: -0.1700
Data Index: 7827519 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0273. Min Range: -7.0273
Max Act: 6.5585. Min Act: -0.1700
Data Index: 7536340 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0273. Min Range: -7.0273
Max Act: 6.5585. Min Act: -0.1700
Data Index: 7024990 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0273. Min Range: -7.0273
Max Act: 6.4960. Min Act: -0.1700
Data Index: 1436621 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0273. Min Range: -7.0273
Max Act: 6.5273. Min Act: -0.1700
Data Index: 3530986 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0273. Min Range: -7.0273
Max Act: 6.4960. Min Act: -0.1700
Data Index: 2150778 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0273. Min Range: -7.0273
Max Act: 6.4960. Min Act: -0.1700
Data Index: 2777346 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0273. Min Range: -7.0273
Max Act: 6.4960. Min Act: -0.1700
Data Index: 6907180 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0273. Min Range: -7.0273
Max Act: 6.4960. Min Act: -0.1700
Data Index: 38648 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0273. Min Range: -7.0273
Max Act: 6.4335. Min Act: -0.1700
Data Index: 5355744 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0273. Min Range: -7.0273
Max Act: 6.4648. Min Act: -0.1700
Data Index: 2957717 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0273. Min Range: -7.0273
Max Act: 6.4335. Min Act: -0.1700
Data Index: 1369757 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0273. Min Range: -7.0273
Max Act: 6.4648. Min Act: -0.1700
Data Index: 6313067 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19