Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1728 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8800. Min Range: -5.8800
Max Act: 5.8800. Min Act: -0.1700
Data Index: 8430257 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8800. Min Range: -5.8800
Max Act: 5.6613. Min Act: -0.1700
Data Index: 614361 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8800. Min Range: -5.8800
Max Act: 5.5675. Min Act: -0.1700
Data Index: 859680 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8800. Min Range: -5.8800
Max Act: 5.5363. Min Act: -0.1700
Data Index: 1746349 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8800. Min Range: -5.8800
Max Act: 5.5050. Min Act: -0.1700
Data Index: 6062182 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8800. Min Range: -5.8800
Max Act: 5.4425. Min Act: -0.1700
Data Index: 5923110 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8800. Min Range: -5.8800
Max Act: 5.4113. Min Act: -0.1700
Data Index: 5286347 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8800. Min Range: -5.8800
Max Act: 5.4113. Min Act: -0.1700
Data Index: 6722437 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8800. Min Range: -5.8800
Max Act: 5.4113. Min Act: -0.1700
Data Index: 7068448 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8800. Min Range: -5.8800
Max Act: 5.3800. Min Act: -0.1700
Data Index: 6595669 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8800. Min Range: -5.8800
Max Act: 5.3800. Min Act: -0.1700
Data Index: 6769890 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8800. Min Range: -5.8800
Max Act: 5.3800. Min Act: -0.1700
Data Index: 8764193 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8800. Min Range: -5.8800
Max Act: 5.3488. Min Act: -0.1700
Data Index: 2419466 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8800. Min Range: -5.8800
Max Act: 5.3488. Min Act: -0.1700
Data Index: 79982 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8800. Min Range: -5.8800
Max Act: 5.3800. Min Act: -0.1700
Data Index: 741179 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8800. Min Range: -5.8800
Max Act: 5.3488. Min Act: -0.1700
Data Index: 8533389 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8800. Min Range: -5.8800
Max Act: 5.3488. Min Act: -0.1700
Data Index: 5785143 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8800. Min Range: -5.8800
Max Act: 5.2863. Min Act: -0.1700
Data Index: 8664135 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8800. Min Range: -5.8800
Max Act: 5.3175. Min Act: -0.1700
Data Index: 5980685 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8800. Min Range: -5.8800
Max Act: 5.2863. Min Act: -0.1700
Data Index: 7135377 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #19