Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3212 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4112. Min Range: -5.4112
Max Act: 5.4112. Min Act: -0.1700
Data Index: 7202778 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4112. Min Range: -5.4112
Max Act: 5.1299. Min Act: -0.1700
Data Index: 7744570 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4112. Min Range: -5.4112
Max Act: 5.1612. Min Act: -0.1700
Data Index: 3779575 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4112. Min Range: -5.4112
Max Act: 5.1299. Min Act: -0.1700
Data Index: 6727989 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4112. Min Range: -5.4112
Max Act: 5.1299. Min Act: -0.1700
Data Index: 8279560 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4112. Min Range: -5.4112
Max Act: 5.0674. Min Act: -0.1700
Data Index: 952679 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4112. Min Range: -5.4112
Max Act: 5.0674. Min Act: -0.1700
Data Index: 4910314 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4112. Min Range: -5.4112
Max Act: 5.0362. Min Act: -0.1700
Data Index: 7942308 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4112. Min Range: -5.4112
Max Act: 5.0362. Min Act: -0.1700
Data Index: 2537650 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4112. Min Range: -5.4112
Max Act: 5.0049. Min Act: -0.1700
Data Index: 7267701 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4112. Min Range: -5.4112
Max Act: 4.9737. Min Act: -0.1700
Data Index: 4089766 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4112. Min Range: -5.4112
Max Act: 4.9424. Min Act: -0.1700
Data Index: 8245057 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4112. Min Range: -5.4112
Max Act: 4.9112. Min Act: -0.1700
Data Index: 3755167 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4112. Min Range: -5.4112
Max Act: 4.9112. Min Act: -0.1700
Data Index: 499029 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4112. Min Range: -5.4112
Max Act: 4.9112. Min Act: -0.1700
Data Index: 5929317 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4112. Min Range: -5.4112
Max Act: 4.8799. Min Act: -0.1700
Data Index: 353742 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4112. Min Range: -5.4112
Max Act: 4.9112. Min Act: -0.1700
Data Index: 6878336 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4112. Min Range: -5.4112
Max Act: 4.8487. Min Act: -0.1700
Data Index: 2472436 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4112. Min Range: -5.4112
Max Act: 4.8174. Min Act: -0.1700
Data Index: 7744239 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4112. Min Range: -5.4112
Max Act: 4.8487. Min Act: -0.1700
Data Index: 7300651 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19