Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1998 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2878. Min Range: -8.2878
Max Act: 8.2878. Min Act: -0.1700
Data Index: 4787994 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2878. Min Range: -8.2878
Max Act: 8.2253. Min Act: -0.1700
Data Index: 1515824 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2878. Min Range: -8.2878
Max Act: 8.0378. Min Act: -0.1700
Data Index: 742138 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2878. Min Range: -8.2878
Max Act: 8.0378. Min Act: -0.1700
Data Index: 8635905 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2878. Min Range: -8.2878
Max Act: 8.0378. Min Act: -0.1700
Data Index: 6457731 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2878. Min Range: -8.2878
Max Act: 8.0378. Min Act: -0.1700
Data Index: 661337 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2878. Min Range: -8.2878
Max Act: 8.0378. Min Act: -0.1700
Data Index: 2170599 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2878. Min Range: -8.2878
Max Act: 8.0378. Min Act: -0.1700
Data Index: 8673525 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2878. Min Range: -8.2878
Max Act: 7.9753. Min Act: -0.1700
Data Index: 8692763 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2878. Min Range: -8.2878
Max Act: 7.9753. Min Act: -0.1700
Data Index: 4124467 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2878. Min Range: -8.2878
Max Act: 7.9128. Min Act: -0.1700
Data Index: 8061429 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2878. Min Range: -8.2878
Max Act: 7.8503. Min Act: -0.1700
Data Index: 4143683 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2878. Min Range: -8.2878
Max Act: 7.8503. Min Act: -0.1700
Data Index: 4416209 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2878. Min Range: -8.2878
Max Act: 7.7878. Min Act: -0.1700
Data Index: 1917565 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2878. Min Range: -8.2878
Max Act: 7.8503. Min Act: -0.1700
Data Index: 814591 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2878. Min Range: -8.2878
Max Act: 7.7878. Min Act: -0.1700
Data Index: 4124464 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2878. Min Range: -8.2878
Max Act: 7.7878. Min Act: -0.1700
Data Index: 8415912 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2878. Min Range: -8.2878
Max Act: 7.7878. Min Act: -0.1700
Data Index: 33819 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2878. Min Range: -8.2878
Max Act: 7.7878. Min Act: -0.1700
Data Index: 3857557 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2878. Min Range: -8.2878
Max Act: 7.7878. Min Act: -0.1700
Data Index: 752282 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19