Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4262 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1529. Min Range: -6.1529
Max Act: 6.1529. Min Act: -0.1700
Data Index: 6286733 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1529. Min Range: -6.1529
Max Act: 5.6529. Min Act: -0.1700
Data Index: 3888994 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1529. Min Range: -6.1529
Max Act: 5.5904. Min Act: -0.1700
Data Index: 1525918 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1529. Min Range: -6.1529
Max Act: 5.6217. Min Act: -0.1700
Data Index: 417090 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1529. Min Range: -6.1529
Max Act: 5.5904. Min Act: -0.1700
Data Index: 646335 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1529. Min Range: -6.1529
Max Act: 5.5904. Min Act: -0.1700
Data Index: 7208271 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1529. Min Range: -6.1529
Max Act: 5.5592. Min Act: -0.1700
Data Index: 6661190 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1529. Min Range: -6.1529
Max Act: 5.5592. Min Act: -0.1700
Data Index: 3381936 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1529. Min Range: -6.1529
Max Act: 5.4967. Min Act: -0.1700
Data Index: 6594408 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1529. Min Range: -6.1529
Max Act: 5.4967. Min Act: -0.1700
Data Index: 7266383 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1529. Min Range: -6.1529
Max Act: 5.4967. Min Act: -0.1700
Data Index: 5090772 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1529. Min Range: -6.1529
Max Act: 5.4967. Min Act: -0.1700
Data Index: 197270 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1529. Min Range: -6.1529
Max Act: 5.4654. Min Act: -0.1700
Data Index: 2238730 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1529. Min Range: -6.1529
Max Act: 5.4654. Min Act: -0.1700
Data Index: 4044557 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1529. Min Range: -6.1529
Max Act: 5.4654. Min Act: -0.1700
Data Index: 1786525 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1529. Min Range: -6.1529
Max Act: 5.4342. Min Act: -0.1700
Data Index: 6248915 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1529. Min Range: -6.1529
Max Act: 5.4342. Min Act: -0.1700
Data Index: 6972592 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1529. Min Range: -6.1529
Max Act: 5.4342. Min Act: -0.1700
Data Index: 8593445 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1529. Min Range: -6.1529
Max Act: 5.4342. Min Act: -0.1700
Data Index: 164219 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1529. Min Range: -6.1529
Max Act: 5.4342. Min Act: -0.1700
Data Index: 7583470 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19