Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2169 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0783. Min Range: -3.0783
Max Act: 3.0783. Min Act: -0.1700
Data Index: 4620058 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0783. Min Range: -3.0783
Max Act: 2.9678. Min Act: -0.1700
Data Index: 8044942 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0783. Min Range: -3.0783
Max Act: 2.9519. Min Act: -0.1700
Data Index: 1268720 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0783. Min Range: -3.0783
Max Act: 2.9678. Min Act: -0.1700
Data Index: 6166317 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0783. Min Range: -3.0783
Max Act: 2.9361. Min Act: -0.1700
Data Index: 1627162 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0783. Min Range: -3.0783
Max Act: 2.9361. Min Act: -0.1700
Data Index: 4663779 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0783. Min Range: -3.0783
Max Act: 2.8885. Min Act: -0.1700
Data Index: 6868533 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0783. Min Range: -3.0783
Max Act: 2.8885. Min Act: -0.1700
Data Index: 8469514 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0783. Min Range: -3.0783
Max Act: 2.9044. Min Act: -0.1700
Data Index: 4874402 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0783. Min Range: -3.0783
Max Act: 2.8727. Min Act: -0.1700
Data Index: 8429574 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0783. Min Range: -3.0783
Max Act: 2.8568. Min Act: -0.1700
Data Index: 5925301 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0783. Min Range: -3.0783
Max Act: 2.8409. Min Act: -0.1700
Data Index: 1429056 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0783. Min Range: -3.0783
Max Act: 2.8250. Min Act: -0.1700
Data Index: 8095304 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0783. Min Range: -3.0783
Max Act: 2.8250. Min Act: -0.1700
Data Index: 921283 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0783. Min Range: -3.0783
Max Act: 2.8250. Min Act: -0.1700
Data Index: 7146237 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0783. Min Range: -3.0783
Max Act: 2.8250. Min Act: -0.1700
Data Index: 8508129 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0783. Min Range: -3.0783
Max Act: 2.8091. Min Act: -0.1700
Data Index: 3626641 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0783. Min Range: -3.0783
Max Act: 2.7932. Min Act: -0.1700
Data Index: 7722546 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0783. Min Range: -3.0783
Max Act: 2.7772. Min Act: -0.1700
Data Index: 6917066 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0783. Min Range: -3.0783
Max Act: 2.7932. Min Act: -0.1700
Data Index: 296782 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #19