Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2900 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6800. Min Range: -5.6800
Max Act: 5.6800. Min Act: -0.1700
Data Index: 6093635 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6800. Min Range: -5.6800
Max Act: 5.5550. Min Act: -0.1700
Data Index: 4640111 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6800. Min Range: -5.6800
Max Act: 5.4925. Min Act: -0.1700
Data Index: 8367708 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6800. Min Range: -5.6800
Max Act: 5.4300. Min Act: -0.1700
Data Index: 6752264 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6800. Min Range: -5.6800
Max Act: 5.4300. Min Act: -0.1700
Data Index: 4027316 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6800. Min Range: -5.6800
Max Act: 5.3988. Min Act: -0.1700
Data Index: 659237 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6800. Min Range: -5.6800
Max Act: 5.3675. Min Act: -0.1700
Data Index: 5918091 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6800. Min Range: -5.6800
Max Act: 5.3363. Min Act: -0.1700
Data Index: 3068159 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6800. Min Range: -5.6800
Max Act: 5.3050. Min Act: -0.1700
Data Index: 835773 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6800. Min Range: -5.6800
Max Act: 5.3050. Min Act: -0.1700
Data Index: 4563769 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6800. Min Range: -5.6800
Max Act: 5.2738. Min Act: -0.1700
Data Index: 704527 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6800. Min Range: -5.6800
Max Act: 5.2425. Min Act: -0.1700
Data Index: 8760871 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6800. Min Range: -5.6800
Max Act: 5.2425. Min Act: -0.1700
Data Index: 7186 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6800. Min Range: -5.6800
Max Act: 5.2738. Min Act: -0.1700
Data Index: 8363587 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6800. Min Range: -5.6800
Max Act: 5.2425. Min Act: -0.1700
Data Index: 8746033 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6800. Min Range: -5.6800
Max Act: 5.2113. Min Act: -0.1700
Data Index: 2679636 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6800. Min Range: -5.6800
Max Act: 5.2113. Min Act: -0.1700
Data Index: 4387865 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6800. Min Range: -5.6800
Max Act: 5.1800. Min Act: -0.1700
Data Index: 3726853 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6800. Min Range: -5.6800
Max Act: 5.1488. Min Act: -0.1700
Data Index: 4815745 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6800. Min Range: -5.6800
Max Act: 5.1800. Min Act: -0.1700
Data Index: 700772 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19