Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1458 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9232. Min Range: -5.9232
Max Act: 5.9232. Min Act: -0.1700
Data Index: 1743216 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9232. Min Range: -5.9232
Max Act: 5.8919. Min Act: -0.1700
Data Index: 6743194 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9232. Min Range: -5.9232
Max Act: 5.7357. Min Act: -0.1700
Data Index: 8172575 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9232. Min Range: -5.9232
Max Act: 5.7044. Min Act: -0.1700
Data Index: 265685 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9232. Min Range: -5.9232
Max Act: 5.7044. Min Act: -0.1700
Data Index: 6467898 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9232. Min Range: -5.9232
Max Act: 5.6419. Min Act: -0.1700
Data Index: 2699067 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9232. Min Range: -5.9232
Max Act: 5.6107. Min Act: -0.1700
Data Index: 8182246 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9232. Min Range: -5.9232
Max Act: 5.5794. Min Act: -0.1700
Data Index: 4867843 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9232. Min Range: -5.9232
Max Act: 5.5482. Min Act: -0.1700
Data Index: 2441146 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9232. Min Range: -5.9232
Max Act: 5.5169. Min Act: -0.1700
Data Index: 2968717 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9232. Min Range: -5.9232
Max Act: 5.4857. Min Act: -0.1700
Data Index: 28938 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9232. Min Range: -5.9232
Max Act: 5.4857. Min Act: -0.1700
Data Index: 8574219 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9232. Min Range: -5.9232
Max Act: 5.4232. Min Act: -0.1700
Data Index: 7695437 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9232. Min Range: -5.9232
Max Act: 5.3919. Min Act: -0.1700
Data Index: 5893846 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9232. Min Range: -5.9232
Max Act: 5.4232. Min Act: -0.1700
Data Index: 5526372 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9232. Min Range: -5.9232
Max Act: 5.3919. Min Act: -0.1700
Data Index: 6828570 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9232. Min Range: -5.9232
Max Act: 5.4544. Min Act: -0.1700
Data Index: 4421150 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9232. Min Range: -5.9232
Max Act: 5.3919. Min Act: -0.1700
Data Index: 7274387 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9232. Min Range: -5.9232
Max Act: 5.3919. Min Act: -0.1700
Data Index: 4409216 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9232. Min Range: -5.9232
Max Act: 5.3607. Min Act: -0.1700
Data Index: 5327620 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19