Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3073 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1959. Min Range: -8.1959
Max Act: 8.1959. Min Act: -0.1700
Data Index: 7795823 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1959. Min Range: -8.1959
Max Act: 8.0084. Min Act: -0.1700
Data Index: 2282397 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1959. Min Range: -8.1959
Max Act: 7.9459. Min Act: -0.1700
Data Index: 7195503 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1959. Min Range: -8.1959
Max Act: 7.7271. Min Act: -0.1700
Data Index: 972228 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1959. Min Range: -8.1959
Max Act: 7.7271. Min Act: -0.1700
Data Index: 6598394 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1959. Min Range: -8.1959
Max Act: 7.6334. Min Act: -0.1700
Data Index: 668040 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1959. Min Range: -8.1959
Max Act: 7.6646. Min Act: -0.1700
Data Index: 7612502 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1959. Min Range: -8.1959
Max Act: 7.5709. Min Act: -0.1700
Data Index: 8356517 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1959. Min Range: -8.1959
Max Act: 7.5084. Min Act: -0.1700
Data Index: 3669843 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1959. Min Range: -8.1959
Max Act: 7.4771. Min Act: -0.1700
Data Index: 2705895 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1959. Min Range: -8.1959
Max Act: 7.4459. Min Act: -0.1700
Data Index: 484197 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1959. Min Range: -8.1959
Max Act: 7.4459. Min Act: -0.1700
Data Index: 6811091 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1959. Min Range: -8.1959
Max Act: 7.4459. Min Act: -0.1700
Data Index: 5083696 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1959. Min Range: -8.1959
Max Act: 7.3834. Min Act: -0.1700
Data Index: 5270259 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1959. Min Range: -8.1959
Max Act: 7.3521. Min Act: -0.1700
Data Index: 3305122 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1959. Min Range: -8.1959
Max Act: 7.3521. Min Act: -0.1700
Data Index: 5382448 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1959. Min Range: -8.1959
Max Act: 7.3521. Min Act: -0.1700
Data Index: 2745329 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1959. Min Range: -8.1959
Max Act: 7.3521. Min Act: -0.1700
Data Index: 1820319 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1959. Min Range: -8.1959
Max Act: 7.3209. Min Act: -0.1700
Data Index: 2155078 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1959. Min Range: -8.1959
Max Act: 7.3209. Min Act: -0.1700
Data Index: 7689875 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19