Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1917 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2081. Min Range: -6.2081
Max Act: 6.2081. Min Act: -0.1700
Data Index: 2527605 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2081. Min Range: -6.2081
Max Act: 6.1769. Min Act: -0.1700
Data Index: 3795844 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2081. Min Range: -6.2081
Max Act: 6.0519. Min Act: -0.1700
Data Index: 7472442 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2081. Min Range: -6.2081
Max Act: 6.0206. Min Act: -0.1700
Data Index: 8521913 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2081. Min Range: -6.2081
Max Act: 5.9894. Min Act: -0.1700
Data Index: 1006981 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2081. Min Range: -6.2081
Max Act: 5.9581. Min Act: -0.1700
Data Index: 7277022 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2081. Min Range: -6.2081
Max Act: 5.9269. Min Act: -0.1700
Data Index: 1402018 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2081. Min Range: -6.2081
Max Act: 5.8956. Min Act: -0.1700
Data Index: 2268196 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2081. Min Range: -6.2081
Max Act: 5.8956. Min Act: -0.1700
Data Index: 7228640 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2081. Min Range: -6.2081
Max Act: 5.8956. Min Act: -0.1700
Data Index: 2539300 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2081. Min Range: -6.2081
Max Act: 5.8956. Min Act: -0.1700
Data Index: 2184855 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2081. Min Range: -6.2081
Max Act: 5.8956. Min Act: -0.1700
Data Index: 4730978 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2081. Min Range: -6.2081
Max Act: 5.8331. Min Act: -0.1700
Data Index: 8666570 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2081. Min Range: -6.2081
Max Act: 5.8331. Min Act: -0.1700
Data Index: 1515315 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2081. Min Range: -6.2081
Max Act: 5.8331. Min Act: -0.1700
Data Index: 1018512 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2081. Min Range: -6.2081
Max Act: 5.8019. Min Act: -0.1700
Data Index: 6772530 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2081. Min Range: -6.2081
Max Act: 5.8019. Min Act: -0.1700
Data Index: 3939952 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2081. Min Range: -6.2081
Max Act: 5.8019. Min Act: -0.1700
Data Index: 6172921 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2081. Min Range: -6.2081
Max Act: 5.8019. Min Act: -0.1700
Data Index: 3741124 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2081. Min Range: -6.2081
Max Act: 5.8019. Min Act: -0.1700
Data Index: 7382939 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19