Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6349 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4454. Min Range: -6.4454
Max Act: 6.4454. Min Act: -0.1700
Data Index: 6229225 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4454. Min Range: -6.4454
Max Act: 6.4141. Min Act: -0.1700
Data Index: 3901312 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4454. Min Range: -6.4454
Max Act: 6.3516. Min Act: -0.1700
Data Index: 6332305 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4454. Min Range: -6.4454
Max Act: 6.3829. Min Act: -0.1700
Data Index: 6871271 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4454. Min Range: -6.4454
Max Act: 6.2891. Min Act: -0.1700
Data Index: 7488096 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4454. Min Range: -6.4454
Max Act: 6.3204. Min Act: -0.1700
Data Index: 2743399 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4454. Min Range: -6.4454
Max Act: 6.3204. Min Act: -0.1700
Data Index: 486289 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4454. Min Range: -6.4454
Max Act: 6.3204. Min Act: -0.1700
Data Index: 5689040 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4454. Min Range: -6.4454
Max Act: 6.2266. Min Act: -0.1700
Data Index: 2929916 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4454. Min Range: -6.4454
Max Act: 6.1954. Min Act: -0.1700
Data Index: 6908450 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4454. Min Range: -6.4454
Max Act: 6.1954. Min Act: -0.1700
Data Index: 7347451 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4454. Min Range: -6.4454
Max Act: 6.1954. Min Act: -0.1700
Data Index: 7612202 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4454. Min Range: -6.4454
Max Act: 6.1641. Min Act: -0.1700
Data Index: 6666681 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4454. Min Range: -6.4454
Max Act: 6.1641. Min Act: -0.1700
Data Index: 5883201 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4454. Min Range: -6.4454
Max Act: 6.1016. Min Act: -0.1700
Data Index: 4321643 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4454. Min Range: -6.4454
Max Act: 6.0704. Min Act: -0.1700
Data Index: 7123001 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4454. Min Range: -6.4454
Max Act: 6.0704. Min Act: -0.1700
Data Index: 8767141 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4454. Min Range: -6.4454
Max Act: 6.0704. Min Act: -0.1700
Data Index: 6505923 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4454. Min Range: -6.4454
Max Act: 6.0391. Min Act: -0.1700
Data Index: 7332238 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4454. Min Range: -6.4454
Max Act: 6.0391. Min Act: -0.1700
Data Index: 5703896 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19