Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5867 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.6124. Min Range: -1.6124
Max Act: 1.6124. Min Act: -0.1700
Data Index: 8174194 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6124. Min Range: -1.6124
Max Act: 1.5949. Min Act: -0.1698
Data Index: 7294751 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6124. Min Range: -1.6124
Max Act: 1.5600. Min Act: -0.1698
Data Index: 5584388 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6124. Min Range: -1.6124
Max Act: 1.5600. Min Act: -0.1700
Data Index: 2944407 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6124. Min Range: -1.6124
Max Act: 1.5425. Min Act: -0.1700
Data Index: 2410769 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6124. Min Range: -1.6124
Max Act: 1.5074. Min Act: -0.1698
Data Index: 1010373 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6124. Min Range: -1.6124
Max Act: 1.4898. Min Act: -0.1684
Data Index: 803832 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6124. Min Range: -1.6124
Max Act: 1.4898. Min Act: -0.1700
Data Index: 7410398 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6124. Min Range: -1.6124
Max Act: 1.5074. Min Act: -0.1681
Data Index: 6929280 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6124. Min Range: -1.6124
Max Act: 1.4898. Min Act: -0.1700
Data Index: 7142733 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6124. Min Range: -1.6124
Max Act: 1.4898. Min Act: -0.1700
Data Index: 3327930 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6124. Min Range: -1.6124
Max Act: 1.4722. Min Act: -0.1700
Data Index: 6816216 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6124. Min Range: -1.6124
Max Act: 1.4722. Min Act: -0.1700
Data Index: 8450027 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6124. Min Range: -1.6124
Max Act: 1.4722. Min Act: -0.1700
Data Index: 3287122 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6124. Min Range: -1.6124
Max Act: 1.4547. Min Act: -0.1700
Data Index: 8579857 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6124. Min Range: -1.6124
Max Act: 1.4547. Min Act: -0.1700
Data Index: 4419978 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6124. Min Range: -1.6124
Max Act: 1.4547. Min Act: -0.1699
Data Index: 8650569 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6124. Min Range: -1.6124
Max Act: 1.4722. Min Act: -0.1700
Data Index: 5835966 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6124. Min Range: -1.6124
Max Act: 1.4547. Min Act: -0.1700
Data Index: 7806470 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6124. Min Range: -1.6124
Max Act: 1.4547. Min Act: -0.1700
Data Index: 6976643 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19