Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2691 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4043. Min Range: -5.4043
Max Act: 5.4043. Min Act: -0.1700
Data Index: 2680081 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4043. Min Range: -5.4043
Max Act: 5.0918. Min Act: -0.1700
Data Index: 4366768 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4043. Min Range: -5.4043
Max Act: 5.0605. Min Act: -0.1700
Data Index: 4249997 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4043. Min Range: -5.4043
Max Act: 5.0293. Min Act: -0.1700
Data Index: 5388683 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4043. Min Range: -5.4043
Max Act: 5.0293. Min Act: -0.1700
Data Index: 242129 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4043. Min Range: -5.4043
Max Act: 5.0293. Min Act: -0.1700
Data Index: 4190861 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4043. Min Range: -5.4043
Max Act: 4.9980. Min Act: -0.1700
Data Index: 7892368 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4043. Min Range: -5.4043
Max Act: 4.9980. Min Act: -0.1700
Data Index: 4723721 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4043. Min Range: -5.4043
Max Act: 4.9668. Min Act: -0.1700
Data Index: 7945027 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4043. Min Range: -5.4043
Max Act: 4.9355. Min Act: -0.1700
Data Index: 5670338 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4043. Min Range: -5.4043
Max Act: 4.9355. Min Act: -0.1700
Data Index: 332026 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4043. Min Range: -5.4043
Max Act: 4.9355. Min Act: -0.1700
Data Index: 1208053 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4043. Min Range: -5.4043
Max Act: 4.8730. Min Act: -0.1700
Data Index: 7098713 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4043. Min Range: -5.4043
Max Act: 4.8730. Min Act: -0.1700
Data Index: 8393749 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4043. Min Range: -5.4043
Max Act: 4.8730. Min Act: -0.1700
Data Index: 1443558 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4043. Min Range: -5.4043
Max Act: 4.8730. Min Act: -0.1700
Data Index: 2745218 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4043. Min Range: -5.4043
Max Act: 4.8418. Min Act: -0.1700
Data Index: 7574453 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4043. Min Range: -5.4043
Max Act: 4.8418. Min Act: -0.1700
Data Index: 2246993 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4043. Min Range: -5.4043
Max Act: 4.7793. Min Act: -0.1700
Data Index: 4771888 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4043. Min Range: -5.4043
Max Act: 4.7793. Min Act: -0.1700
Data Index: 475789 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19