Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1910 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.2467. Min Range: -10.2467
Max Act: 10.2467. Min Act: -0.1700
Data Index: 1140663 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2467. Min Range: -10.2467
Max Act: 10.1217. Min Act: -0.1700
Data Index: 299262 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2467. Min Range: -10.2467
Max Act: 9.9967. Min Act: -0.1700
Data Index: 4970372 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2467. Min Range: -10.2467
Max Act: 9.9342. Min Act: -0.1700
Data Index: 3886994 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2467. Min Range: -10.2467
Max Act: 9.9342. Min Act: -0.1700
Data Index: 1067181 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2467. Min Range: -10.2467
Max Act: 9.8092. Min Act: -0.1700
Data Index: 431383 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2467. Min Range: -10.2467
Max Act: 9.9342. Min Act: -0.1700
Data Index: 1897222 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2467. Min Range: -10.2467
Max Act: 9.8092. Min Act: -0.1700
Data Index: 757248 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2467. Min Range: -10.2467
Max Act: 9.9342. Min Act: -0.1700
Data Index: 7327512 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2467. Min Range: -10.2467
Max Act: 9.7467. Min Act: -0.1700
Data Index: 5950103 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2467. Min Range: -10.2467
Max Act: 9.7467. Min Act: -0.1700
Data Index: 1509185 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2467. Min Range: -10.2467
Max Act: 9.6842. Min Act: -0.1700
Data Index: 6388923 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2467. Min Range: -10.2467
Max Act: 9.7467. Min Act: -0.1700
Data Index: 2085382 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2467. Min Range: -10.2467
Max Act: 9.6842. Min Act: -0.1700
Data Index: 5761870 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2467. Min Range: -10.2467
Max Act: 9.6842. Min Act: -0.1700
Data Index: 1920219 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2467. Min Range: -10.2467
Max Act: 9.5592. Min Act: -0.1700
Data Index: 2954997 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2467. Min Range: -10.2467
Max Act: 9.6217. Min Act: -0.1700
Data Index: 6281960 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2467. Min Range: -10.2467
Max Act: 9.6217. Min Act: -0.1700
Data Index: 669028 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2467. Min Range: -10.2467
Max Act: 9.6217. Min Act: -0.1700
Data Index: 1329250 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2467. Min Range: -10.2467
Max Act: 9.5592. Min Act: -0.1700
Data Index: 3404821 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #19