Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5521 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4618. Min Range: -3.4618
Max Act: 3.4618. Min Act: -0.1700
Data Index: 4180711 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4618. Min Range: -3.4618
Max Act: 3.4305. Min Act: -0.1700
Data Index: 8725544 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4618. Min Range: -3.4618
Max Act: 3.3834. Min Act: -0.1700
Data Index: 3007207 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4618. Min Range: -3.4618
Max Act: 3.3521. Min Act: -0.1700
Data Index: 1635762 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4618. Min Range: -3.4618
Max Act: 3.3521. Min Act: -0.1700
Data Index: 2135068 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4618. Min Range: -3.4618
Max Act: 3.3050. Min Act: -0.1700
Data Index: 8555432 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4618. Min Range: -3.4618
Max Act: 3.3207. Min Act: -0.1700
Data Index: 5624621 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4618. Min Range: -3.4618
Max Act: 3.3364. Min Act: -0.1700
Data Index: 7636184 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4618. Min Range: -3.4618
Max Act: 3.3050. Min Act: -0.1700
Data Index: 6201050 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4618. Min Range: -3.4618
Max Act: 3.2893. Min Act: -0.1700
Data Index: 6600453 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4618. Min Range: -3.4618
Max Act: 3.2893. Min Act: -0.1700
Data Index: 1449136 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4618. Min Range: -3.4618
Max Act: 3.2736. Min Act: -0.1700
Data Index: 3087028 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4618. Min Range: -3.4618
Max Act: 3.2736. Min Act: -0.1700
Data Index: 1130997 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4618. Min Range: -3.4618
Max Act: 3.2579. Min Act: -0.1700
Data Index: 4320747 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4618. Min Range: -3.4618
Max Act: 3.2422. Min Act: -0.1700
Data Index: 7364459 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4618. Min Range: -3.4618
Max Act: 3.2264. Min Act: -0.1700
Data Index: 2585431 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4618. Min Range: -3.4618
Max Act: 3.2264. Min Act: -0.1700
Data Index: 3029052 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4618. Min Range: -3.4618
Max Act: 3.2264. Min Act: -0.1700
Data Index: 1937769 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4618. Min Range: -3.4618
Max Act: 3.2107. Min Act: -0.1700
Data Index: 7123060 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4618. Min Range: -3.4618
Max Act: 3.2107. Min Act: -0.1700
Data Index: 2193094 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #19