Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4027 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6760. Min Range: -5.6760
Max Act: 5.6760. Min Act: -0.1700
Data Index: 7934291 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6760. Min Range: -5.6760
Max Act: 5.5822. Min Act: -0.1700
Data Index: 6291858 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6760. Min Range: -5.6760
Max Act: 5.5510. Min Act: -0.1700
Data Index: 5040332 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6760. Min Range: -5.6760
Max Act: 5.5197. Min Act: -0.1700
Data Index: 6135528 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6760. Min Range: -5.6760
Max Act: 5.4885. Min Act: -0.1700
Data Index: 313493 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6760. Min Range: -5.6760
Max Act: 5.4260. Min Act: -0.1700
Data Index: 4642280 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6760. Min Range: -5.6760
Max Act: 5.3947. Min Act: -0.1700
Data Index: 4536843 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6760. Min Range: -5.6760
Max Act: 5.3947. Min Act: -0.1700
Data Index: 7317351 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6760. Min Range: -5.6760
Max Act: 5.3635. Min Act: -0.1700
Data Index: 2623111 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6760. Min Range: -5.6760
Max Act: 5.3635. Min Act: -0.1700
Data Index: 8285167 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6760. Min Range: -5.6760
Max Act: 5.3322. Min Act: -0.1700
Data Index: 3241479 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6760. Min Range: -5.6760
Max Act: 5.3322. Min Act: -0.1700
Data Index: 19864 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6760. Min Range: -5.6760
Max Act: 5.3010. Min Act: -0.1700
Data Index: 6199238 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6760. Min Range: -5.6760
Max Act: 5.3010. Min Act: -0.1700
Data Index: 8285164 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6760. Min Range: -5.6760
Max Act: 5.3010. Min Act: -0.1700
Data Index: 4130730 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6760. Min Range: -5.6760
Max Act: 5.3010. Min Act: -0.1700
Data Index: 1139957 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6760. Min Range: -5.6760
Max Act: 5.3010. Min Act: -0.1700
Data Index: 1970473 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6760. Min Range: -5.6760
Max Act: 5.3010. Min Act: -0.1700
Data Index: 6138893 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6760. Min Range: -5.6760
Max Act: 5.3010. Min Act: -0.1700
Data Index: 6230120 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6760. Min Range: -5.6760
Max Act: 5.2697. Min Act: -0.1700
Data Index: 188245 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #19