Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5937 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.8226. Min Act: -0.1700
Data Index: 6311787 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.7289. Min Act: -0.1700
Data Index: 1887802 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.6976. Min Act: -0.1700
Data Index: 6049231 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.6664. Min Act: -0.1700
Data Index: 6250372 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.6664. Min Act: -0.1700
Data Index: 1600077 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.6976. Min Act: -0.1700
Data Index: 7510978 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.6351. Min Act: -0.1700
Data Index: 4701343 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.6351. Min Act: -0.1700
Data Index: 4923187 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.6351. Min Act: -0.1700
Data Index: 3358690 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.6351. Min Act: -0.1700
Data Index: 1112486 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.6351. Min Act: -0.1700
Data Index: 1335191 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.6351. Min Act: -0.1700
Data Index: 5809277 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.6039. Min Act: -0.1700
Data Index: 5165513 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.6039. Min Act: -0.1700
Data Index: 1600064 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.6039. Min Act: -0.1700
Data Index: 1600078 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.5726. Min Act: -0.1700
Data Index: 462749 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.5726. Min Act: -0.1700
Data Index: 7998160 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.5726. Min Act: -0.1700
Data Index: 3082780 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.5414. Min Act: -0.1700
Data Index: 4849545 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.5414. Min Act: -0.1700
Data Index: 279785 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19