Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4066 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.4491. Min Range: -9.4491
Max Act: 9.4491. Min Act: -0.1700
Data Index: 3717516 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4491. Min Range: -9.4491
Max Act: 9.3866. Min Act: -0.1700
Data Index: 8495554 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4491. Min Range: -9.4491
Max Act: 9.4491. Min Act: -0.1700
Data Index: 8155258 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4491. Min Range: -9.4491
Max Act: 9.3241. Min Act: -0.1700
Data Index: 631166 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4491. Min Range: -9.4491
Max Act: 9.3241. Min Act: -0.1700
Data Index: 1251747 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4491. Min Range: -9.4491
Max Act: 9.2616. Min Act: -0.1700
Data Index: 7805731 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4491. Min Range: -9.4491
Max Act: 9.2616. Min Act: -0.1700
Data Index: 3827845 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4491. Min Range: -9.4491
Max Act: 9.1991. Min Act: -0.1700
Data Index: 746319 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4491. Min Range: -9.4491
Max Act: 9.2616. Min Act: -0.1700
Data Index: 1887244 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4491. Min Range: -9.4491
Max Act: 9.1366. Min Act: -0.1700
Data Index: 6097053 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4491. Min Range: -9.4491
Max Act: 9.1366. Min Act: -0.1700
Data Index: 3190137 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4491. Min Range: -9.4491
Max Act: 9.1366. Min Act: -0.1700
Data Index: 8141201 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4491. Min Range: -9.4491
Max Act: 9.1991. Min Act: -0.1700
Data Index: 1093257 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4491. Min Range: -9.4491
Max Act: 9.1991. Min Act: -0.1700
Data Index: 6729597 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4491. Min Range: -9.4491
Max Act: 9.0741. Min Act: -0.1700
Data Index: 3953534 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4491. Min Range: -9.4491
Max Act: 9.0741. Min Act: -0.1700
Data Index: 1176456 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4491. Min Range: -9.4491
Max Act: 9.1366. Min Act: -0.1700
Data Index: 8628358 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4491. Min Range: -9.4491
Max Act: 9.0741. Min Act: -0.1700
Data Index: 4442980 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4491. Min Range: -9.4491
Max Act: 8.9491. Min Act: -0.1700
Data Index: 6096362 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4491. Min Range: -9.4491
Max Act: 9.0741. Min Act: -0.1700
Data Index: 4090768 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19