Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5444 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8220. Min Range: -5.8220
Max Act: 5.8220. Min Act: -0.1700
Data Index: 7166683 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8220. Min Range: -5.8220
Max Act: 5.7907. Min Act: -0.1700
Data Index: 7166684 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8220. Min Range: -5.8220
Max Act: 5.7595. Min Act: -0.1700
Data Index: 7166673 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8220. Min Range: -5.8220
Max Act: 5.7595. Min Act: -0.1700
Data Index: 2396107 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8220. Min Range: -5.8220
Max Act: 5.7595. Min Act: -0.1700
Data Index: 7166682 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8220. Min Range: -5.8220
Max Act: 5.6970. Min Act: -0.1700
Data Index: 7166681 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8220. Min Range: -5.8220
Max Act: 5.6345. Min Act: -0.1700
Data Index: 7166680 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8220. Min Range: -5.8220
Max Act: 5.6345. Min Act: -0.1700
Data Index: 7521099 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8220. Min Range: -5.8220
Max Act: 5.6345. Min Act: -0.1700
Data Index: 7166677 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8220. Min Range: -5.8220
Max Act: 5.6032. Min Act: -0.1700
Data Index: 1515262 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8220. Min Range: -5.8220
Max Act: 5.6032. Min Act: -0.1700
Data Index: 7166685 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8220. Min Range: -5.8220
Max Act: 5.5720. Min Act: -0.1700
Data Index: 1284965 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8220. Min Range: -5.8220
Max Act: 5.5720. Min Act: -0.1700
Data Index: 7166679 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8220. Min Range: -5.8220
Max Act: 5.5720. Min Act: -0.1700
Data Index: 4146345 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8220. Min Range: -5.8220
Max Act: 5.5407. Min Act: -0.1700
Data Index: 4387897 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8220. Min Range: -5.8220
Max Act: 5.5407. Min Act: -0.1700
Data Index: 5164247 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8220. Min Range: -5.8220
Max Act: 5.4782. Min Act: -0.1700
Data Index: 2742857 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8220. Min Range: -5.8220
Max Act: 5.4470. Min Act: -0.1700
Data Index: 4889207 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8220. Min Range: -5.8220
Max Act: 5.4157. Min Act: -0.1700
Data Index: 682547 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8220. Min Range: -5.8220
Max Act: 5.4157. Min Act: -0.1700
Data Index: 7166686 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19