Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1171 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.3482. Min Act: -0.1700
Data Index: 5073801 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.2857. Min Act: -0.1700
Data Index: 2387470 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.2232. Min Act: -0.1700
Data Index: 4420435 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.2232. Min Act: -0.1700
Data Index: 6539440 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.1607. Min Act: -0.1697
Data Index: 4245262 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.1295. Min Act: -0.1700
Data Index: 3966703 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.1295. Min Act: -0.1700
Data Index: 5510208 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.1295. Min Act: -0.1700
Data Index: 4204216 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0982. Min Act: -0.1700
Data Index: 4097461 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0982. Min Act: -0.1700
Data Index: 4070202 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0670. Min Act: -0.1700
Data Index: 5482090 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0670. Min Act: -0.1700
Data Index: 1317546 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0670. Min Act: -0.1700
Data Index: 8366283 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0670. Min Act: -0.1700
Data Index: 206375 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0357. Min Act: -0.1700
Data Index: 5694243 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0357. Min Act: -0.1700
Data Index: 8599913 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0357. Min Act: -0.1700
Data Index: 2305208 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0357. Min Act: -0.1700
Data Index: 4891448 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0357. Min Act: -0.1700
Data Index: 250077 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0045. Min Act: -0.1700
Data Index: 645116 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19