Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3557 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0887. Min Range: -5.0887
Max Act: 5.0887. Min Act: -0.1700
Data Index: 1103170 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0887. Min Range: -5.0887
Max Act: 4.9950. Min Act: -0.1700
Data Index: 856518 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0887. Min Range: -5.0887
Max Act: 4.9637. Min Act: -0.1700
Data Index: 1362971 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0887. Min Range: -5.0887
Max Act: 4.9637. Min Act: -0.1700
Data Index: 1244997 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0887. Min Range: -5.0887
Max Act: 4.8075. Min Act: -0.1700
Data Index: 2353046 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0887. Min Range: -5.0887
Max Act: 4.7762. Min Act: -0.1700
Data Index: 7144095 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0887. Min Range: -5.0887
Max Act: 4.7450. Min Act: -0.1700
Data Index: 1861018 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0887. Min Range: -5.0887
Max Act: 4.7762. Min Act: -0.1700
Data Index: 8218646 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0887. Min Range: -5.0887
Max Act: 4.7450. Min Act: -0.1700
Data Index: 4056966 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0887. Min Range: -5.0887
Max Act: 4.6825. Min Act: -0.1700
Data Index: 3700836 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0887. Min Range: -5.0887
Max Act: 4.6512. Min Act: -0.1700
Data Index: 7552054 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0887. Min Range: -5.0887
Max Act: 4.6825. Min Act: -0.1700
Data Index: 472505 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0887. Min Range: -5.0887
Max Act: 4.6825. Min Act: -0.1700
Data Index: 1693855 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0887. Min Range: -5.0887
Max Act: 4.6825. Min Act: -0.1700
Data Index: 3063347 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0887. Min Range: -5.0887
Max Act: 4.6512. Min Act: -0.1700
Data Index: 403809 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0887. Min Range: -5.0887
Max Act: 4.6200. Min Act: -0.1700
Data Index: 1091512 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0887. Min Range: -5.0887
Max Act: 4.6512. Min Act: -0.1700
Data Index: 1863152 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0887. Min Range: -5.0887
Max Act: 4.6512. Min Act: -0.1700
Data Index: 8518751 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0887. Min Range: -5.0887
Max Act: 4.6512. Min Act: -0.1700
Data Index: 5017324 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0887. Min Range: -5.0887
Max Act: 4.6512. Min Act: -0.1700
Data Index: 6359884 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19