Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4435 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3166. Min Range: -3.3166
Max Act: 3.3166. Min Act: -0.1700
Data Index: 5314839 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3166. Min Range: -3.3166
Max Act: 3.2381. Min Act: -0.1700
Data Index: 1205719 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3166. Min Range: -3.3166
Max Act: 3.2066. Min Act: -0.1700
Data Index: 2043398 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3166. Min Range: -3.3166
Max Act: 3.1909. Min Act: -0.1700
Data Index: 2753306 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3166. Min Range: -3.3166
Max Act: 3.1909. Min Act: -0.1700
Data Index: 4913401 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3166. Min Range: -3.3166
Max Act: 3.1437. Min Act: -0.1700
Data Index: 7604258 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3166. Min Range: -3.3166
Max Act: 3.1279. Min Act: -0.1700
Data Index: 5765363 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3166. Min Range: -3.3166
Max Act: 3.1279. Min Act: -0.1700
Data Index: 5325351 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3166. Min Range: -3.3166
Max Act: 3.1122. Min Act: -0.1700
Data Index: 498737 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3166. Min Range: -3.3166
Max Act: 3.1122. Min Act: -0.1700
Data Index: 6586052 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3166. Min Range: -3.3166
Max Act: 3.0964. Min Act: -0.1700
Data Index: 5765366 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3166. Min Range: -3.3166
Max Act: 3.0964. Min Act: -0.1700
Data Index: 865570 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3166. Min Range: -3.3166
Max Act: 3.0964. Min Act: -0.1700
Data Index: 1837574 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3166. Min Range: -3.3166
Max Act: 3.0807. Min Act: -0.1700
Data Index: 486611 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3166. Min Range: -3.3166
Max Act: 3.0649. Min Act: -0.1700
Data Index: 3122084 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3166. Min Range: -3.3166
Max Act: 3.0807. Min Act: -0.1700
Data Index: 3886727 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3166. Min Range: -3.3166
Max Act: 3.0491. Min Act: -0.1700
Data Index: 3876852 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3166. Min Range: -3.3166
Max Act: 3.0491. Min Act: -0.1700
Data Index: 5957675 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3166. Min Range: -3.3166
Max Act: 3.0491. Min Act: -0.1700
Data Index: 4377101 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3166. Min Range: -3.3166
Max Act: 3.0333. Min Act: -0.1700
Data Index: 1544785 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #19