Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3039 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1170. Min Range: -4.1170
Max Act: 4.0857. Min Act: -0.1700
Data Index: 8543133 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1170. Min Range: -4.1170
Max Act: 4.1170. Min Act: -0.1700
Data Index: 1548656 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1170. Min Range: -4.1170
Max Act: 4.0545. Min Act: -0.1700
Data Index: 3058296 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1170. Min Range: -4.1170
Max Act: 3.9919. Min Act: -0.1700
Data Index: 4759915 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1170. Min Range: -4.1170
Max Act: 3.9919. Min Act: -0.1700
Data Index: 972119 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1170. Min Range: -4.1170
Max Act: 3.9919. Min Act: -0.1700
Data Index: 4085177 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1170. Min Range: -4.1170
Max Act: 3.9919. Min Act: -0.1700
Data Index: 5700348 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1170. Min Range: -4.1170
Max Act: 3.9607. Min Act: -0.1700
Data Index: 8510901 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1170. Min Range: -4.1170
Max Act: 3.9607. Min Act: -0.1700
Data Index: 3956498 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1170. Min Range: -4.1170
Max Act: 3.9607. Min Act: -0.1700
Data Index: 1603969 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1170. Min Range: -4.1170
Max Act: 3.9919. Min Act: -0.1700
Data Index: 3238776 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1170. Min Range: -4.1170
Max Act: 3.9294. Min Act: -0.1700
Data Index: 5404383 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1170. Min Range: -4.1170
Max Act: 3.9294. Min Act: -0.1700
Data Index: 1961545 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1170. Min Range: -4.1170
Max Act: 3.8982. Min Act: -0.1700
Data Index: 3238761 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1170. Min Range: -4.1170
Max Act: 3.8982. Min Act: -0.1700
Data Index: 2095093 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1170. Min Range: -4.1170
Max Act: 3.8982. Min Act: -0.1700
Data Index: 4818640 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1170. Min Range: -4.1170
Max Act: 3.9294. Min Act: -0.1700
Data Index: 5404378 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1170. Min Range: -4.1170
Max Act: 3.8982. Min Act: -0.1700
Data Index: 4759914 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1170. Min Range: -4.1170
Max Act: 3.8982. Min Act: -0.1700
Data Index: 3208032 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1170. Min Range: -4.1170
Max Act: 3.8982. Min Act: -0.1700
Data Index: 3181777 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19