Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3659 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5712. Min Range: -8.5712
Max Act: 8.5712. Min Act: -0.1700
Data Index: 4521170 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5712. Min Range: -8.5712
Max Act: 8.3837. Min Act: -0.1700
Data Index: 8170690 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5712. Min Range: -8.5712
Max Act: 8.1962. Min Act: -0.1700
Data Index: 7092866 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5712. Min Range: -8.5712
Max Act: 8.1337. Min Act: -0.1700
Data Index: 3503825 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5712. Min Range: -8.5712
Max Act: 8.0712. Min Act: -0.1700
Data Index: 7770522 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5712. Min Range: -8.5712
Max Act: 8.0712. Min Act: -0.1700
Data Index: 2923972 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5712. Min Range: -8.5712
Max Act: 8.0087. Min Act: -0.1700
Data Index: 7429076 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5712. Min Range: -8.5712
Max Act: 8.0087. Min Act: -0.1700
Data Index: 1363044 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5712. Min Range: -8.5712
Max Act: 7.9775. Min Act: -0.1700
Data Index: 2603173 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5712. Min Range: -8.5712
Max Act: 7.9462. Min Act: -0.1700
Data Index: 5521100 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5712. Min Range: -8.5712
Max Act: 7.9462. Min Act: -0.1700
Data Index: 3893734 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5712. Min Range: -8.5712
Max Act: 7.9150. Min Act: -0.1700
Data Index: 1628425 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5712. Min Range: -8.5712
Max Act: 7.8525. Min Act: -0.1700
Data Index: 4491975 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5712. Min Range: -8.5712
Max Act: 7.8837. Min Act: -0.1700
Data Index: 3108912 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5712. Min Range: -8.5712
Max Act: 7.8837. Min Act: -0.1700
Data Index: 6701135 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5712. Min Range: -8.5712
Max Act: 7.8525. Min Act: -0.1700
Data Index: 5022198 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5712. Min Range: -8.5712
Max Act: 7.8525. Min Act: -0.1700
Data Index: 7710360 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5712. Min Range: -8.5712
Max Act: 7.7900. Min Act: -0.1700
Data Index: 752471 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5712. Min Range: -8.5712
Max Act: 7.8212. Min Act: -0.1700
Data Index: 3050248 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5712. Min Range: -8.5712
Max Act: 7.8212. Min Act: -0.1700
Data Index: 2430474 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19