Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4585 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9830. Min Range: -3.9830
Max Act: 3.9830. Min Act: -0.1700
Data Index: 8291546 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9830. Min Range: -3.9830
Max Act: 3.8892. Min Act: -0.1700
Data Index: 229420 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9830. Min Range: -3.9830
Max Act: 3.8267. Min Act: -0.1700
Data Index: 3517158 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9830. Min Range: -3.9830
Max Act: 3.7954. Min Act: -0.1700
Data Index: 4676947 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9830. Min Range: -3.9830
Max Act: 3.7954. Min Act: -0.1700
Data Index: 1739792 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9830. Min Range: -3.9830
Max Act: 3.7641. Min Act: -0.1700
Data Index: 7818579 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9830. Min Range: -3.9830
Max Act: 3.7954. Min Act: -0.1700
Data Index: 92516 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9830. Min Range: -3.9830
Max Act: 3.7954. Min Act: -0.1700
Data Index: 5263396 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9830. Min Range: -3.9830
Max Act: 3.7954. Min Act: -0.1700
Data Index: 3041290 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9830. Min Range: -3.9830
Max Act: 3.7641. Min Act: -0.1700
Data Index: 1394180 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9830. Min Range: -3.9830
Max Act: 3.7641. Min Act: -0.1700
Data Index: 5622238 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9830. Min Range: -3.9830
Max Act: 3.7641. Min Act: -0.1700
Data Index: 5067672 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9830. Min Range: -3.9830
Max Act: 3.7641. Min Act: -0.1700
Data Index: 3710705 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9830. Min Range: -3.9830
Max Act: 3.7641. Min Act: -0.1700
Data Index: 8765887 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9830. Min Range: -3.9830
Max Act: 3.7954. Min Act: -0.1700
Data Index: 493384 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9830. Min Range: -3.9830
Max Act: 3.7641. Min Act: -0.1700
Data Index: 6451240 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9830. Min Range: -3.9830
Max Act: 3.7641. Min Act: -0.1700
Data Index: 532498 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9830. Min Range: -3.9830
Max Act: 3.7329. Min Act: -0.1700
Data Index: 3502085 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9830. Min Range: -3.9830
Max Act: 3.7329. Min Act: -0.1700
Data Index: 370025 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9830. Min Range: -3.9830
Max Act: 3.7329. Min Act: -0.1700
Data Index: 5823106 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19