Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 172 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.2586. Min Act: -0.1700
Data Index: 2787653 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.2429. Min Act: -0.1700
Data Index: 4283127 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.1957. Min Act: -0.1700
Data Index: 6154312 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.1957. Min Act: -0.1700
Data Index: 4018122 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.1800. Min Act: -0.1700
Data Index: 4467882 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.1642. Min Act: -0.1700
Data Index: 2888008 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.0855. Min Act: -0.1700
Data Index: 2003703 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.0855. Min Act: -0.1700
Data Index: 2339155 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.0855. Min Act: -0.1700
Data Index: 8038189 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.1013. Min Act: -0.1700
Data Index: 3718984 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.0539. Min Act: -0.1700
Data Index: 5808191 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.0382. Min Act: -0.1700
Data Index: 4191305 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.0382. Min Act: -0.1700
Data Index: 5509353 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.0066. Min Act: -0.1700
Data Index: 202207 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.0066. Min Act: -0.1700
Data Index: 7880926 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2586. Min Range: -3.2586
Max Act: 2.9750. Min Act: -0.1700
Data Index: 5331254 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2586. Min Range: -3.2586
Max Act: 2.9750. Min Act: -0.1700
Data Index: 4121079 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2586. Min Range: -3.2586
Max Act: 2.9908. Min Act: -0.1700
Data Index: 2930453 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2586. Min Range: -3.2586
Max Act: 2.9750. Min Act: -0.1700
Data Index: 2123820 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2586. Min Range: -3.2586
Max Act: 2.9750. Min Act: -0.1700
Data Index: 3309107 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #19