Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6012 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8158. Min Range: -6.8158
Max Act: 6.8158. Min Act: -0.1700
Data Index: 2562059 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8158. Min Range: -6.8158
Max Act: 6.8158. Min Act: -0.1700
Data Index: 2875255 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8158. Min Range: -6.8158
Max Act: 6.8158. Min Act: -0.1700
Data Index: 2038820 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8158. Min Range: -6.8158
Max Act: 6.6908. Min Act: -0.1700
Data Index: 151613 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8158. Min Range: -6.8158
Max Act: 6.7220. Min Act: -0.1700
Data Index: 8796721 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8158. Min Range: -6.8158
Max Act: 6.6595. Min Act: -0.1700
Data Index: 3385042 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8158. Min Range: -6.8158
Max Act: 6.6595. Min Act: -0.1700
Data Index: 4516885 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8158. Min Range: -6.8158
Max Act: 6.5970. Min Act: -0.1700
Data Index: 4611744 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8158. Min Range: -6.8158
Max Act: 6.6283. Min Act: -0.1700
Data Index: 7831777 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8158. Min Range: -6.8158
Max Act: 6.5970. Min Act: -0.1700
Data Index: 5608829 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8158. Min Range: -6.8158
Max Act: 6.5970. Min Act: -0.1700
Data Index: 2995538 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8158. Min Range: -6.8158
Max Act: 6.5970. Min Act: -0.1700
Data Index: 8345909 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8158. Min Range: -6.8158
Max Act: 6.5345. Min Act: -0.1700
Data Index: 726512 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8158. Min Range: -6.8158
Max Act: 6.5345. Min Act: -0.1700
Data Index: 8663258 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8158. Min Range: -6.8158
Max Act: 6.5658. Min Act: -0.1700
Data Index: 1779891 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8158. Min Range: -6.8158
Max Act: 6.5345. Min Act: -0.1700
Data Index: 221141 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8158. Min Range: -6.8158
Max Act: 6.5033. Min Act: -0.1700
Data Index: 1791338 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8158. Min Range: -6.8158
Max Act: 6.5033. Min Act: -0.1700
Data Index: 6525558 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8158. Min Range: -6.8158
Max Act: 6.4720. Min Act: -0.1700
Data Index: 1395962 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8158. Min Range: -6.8158
Max Act: 6.4720. Min Act: -0.1700
Data Index: 555363 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19