Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3281 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0607. Min Range: -7.0607
Max Act: 7.0607. Min Act: -0.1700
Data Index: 429787 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0607. Min Range: -7.0607
Max Act: 7.0295. Min Act: -0.1700
Data Index: 8697880 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0607. Min Range: -7.0607
Max Act: 6.8420. Min Act: -0.1700
Data Index: 1976005 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0607. Min Range: -7.0607
Max Act: 6.7482. Min Act: -0.1700
Data Index: 93335 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0607. Min Range: -7.0607
Max Act: 6.5920. Min Act: -0.1700
Data Index: 3212359 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0607. Min Range: -7.0607
Max Act: 6.5295. Min Act: -0.1700
Data Index: 3440405 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0607. Min Range: -7.0607
Max Act: 6.5607. Min Act: -0.1700
Data Index: 4168931 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0607. Min Range: -7.0607
Max Act: 6.5295. Min Act: -0.1700
Data Index: 114177 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0607. Min Range: -7.0607
Max Act: 6.4982. Min Act: -0.1700
Data Index: 8715902 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0607. Min Range: -7.0607
Max Act: 6.4357. Min Act: -0.1700
Data Index: 2117785 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0607. Min Range: -7.0607
Max Act: 6.4045. Min Act: -0.1700
Data Index: 4406681 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0607. Min Range: -7.0607
Max Act: 6.4045. Min Act: -0.1700
Data Index: 3243050 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0607. Min Range: -7.0607
Max Act: 6.4045. Min Act: -0.1700
Data Index: 2473112 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0607. Min Range: -7.0607
Max Act: 6.4045. Min Act: -0.1700
Data Index: 5448328 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0607. Min Range: -7.0607
Max Act: 6.4357. Min Act: -0.1700
Data Index: 1364638 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0607. Min Range: -7.0607
Max Act: 6.4045. Min Act: -0.1700
Data Index: 3079505 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0607. Min Range: -7.0607
Max Act: 6.3732. Min Act: -0.1700
Data Index: 6705422 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0607. Min Range: -7.0607
Max Act: 6.3732. Min Act: -0.1700
Data Index: 2084055 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0607. Min Range: -7.0607
Max Act: 6.3732. Min Act: -0.1700
Data Index: 8715895 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0607. Min Range: -7.0607
Max Act: 6.3420. Min Act: -0.1700
Data Index: 7970707 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19