Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4997 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6807. Min Range: -6.6807
Max Act: 6.6807. Min Act: -0.1700
Data Index: 1412773 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6807. Min Range: -6.6807
Max Act: 6.6182. Min Act: -0.1700
Data Index: 5840322 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6807. Min Range: -6.6807
Max Act: 6.6495. Min Act: -0.1700
Data Index: 3359703 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6807. Min Range: -6.6807
Max Act: 6.6495. Min Act: -0.1700
Data Index: 3729411 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6807. Min Range: -6.6807
Max Act: 6.6495. Min Act: -0.1700
Data Index: 1690310 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6807. Min Range: -6.6807
Max Act: 6.6182. Min Act: -0.1700
Data Index: 1816274 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6807. Min Range: -6.6807
Max Act: 6.5557. Min Act: -0.1700
Data Index: 4491189 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6807. Min Range: -6.6807
Max Act: 6.5870. Min Act: -0.1700
Data Index: 8176198 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6807. Min Range: -6.6807
Max Act: 6.5870. Min Act: -0.1700
Data Index: 1885075 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6807. Min Range: -6.6807
Max Act: 6.5557. Min Act: -0.1700
Data Index: 3358204 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6807. Min Range: -6.6807
Max Act: 6.5245. Min Act: -0.1700
Data Index: 1388867 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6807. Min Range: -6.6807
Max Act: 6.5245. Min Act: -0.1700
Data Index: 3749409 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6807. Min Range: -6.6807
Max Act: 6.5245. Min Act: -0.1700
Data Index: 7953364 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6807. Min Range: -6.6807
Max Act: 6.5245. Min Act: -0.1700
Data Index: 2643321 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6807. Min Range: -6.6807
Max Act: 6.5245. Min Act: -0.1700
Data Index: 2053985 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6807. Min Range: -6.6807
Max Act: 6.4932. Min Act: -0.1700
Data Index: 1580513 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6807. Min Range: -6.6807
Max Act: 6.4932. Min Act: -0.1700
Data Index: 3389138 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6807. Min Range: -6.6807
Max Act: 6.4620. Min Act: -0.1700
Data Index: 7067977 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6807. Min Range: -6.6807
Max Act: 6.4620. Min Act: -0.1700
Data Index: 801734 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6807. Min Range: -6.6807
Max Act: 6.4932. Min Act: -0.1700
Data Index: 7042611 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19