Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4441 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7029. Min Range: -4.7029
Max Act: 4.7029. Min Act: -0.1684
Data Index: 5844882 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7029. Min Range: -4.7029
Max Act: 4.3904. Min Act: -0.1561
Data Index: 3762187 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7029. Min Range: -4.7029
Max Act: 4.2966. Min Act: -0.1582
Data Index: 3762178 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7029. Min Range: -4.7029
Max Act: 4.2654. Min Act: -0.1625
Data Index: 3762172 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7029. Min Range: -4.7029
Max Act: 4.2341. Min Act: -0.1645
Data Index: 3724937 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7029. Min Range: -4.7029
Max Act: 4.2341. Min Act: -0.1683
Data Index: 3762175 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7029. Min Range: -4.7029
Max Act: 4.2341. Min Act: -0.1700
Data Index: 3762168 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7029. Min Range: -4.7029
Max Act: 4.1404. Min Act: -0.1700
Data Index: 5225667 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7029. Min Range: -4.7029
Max Act: 4.1404. Min Act: -0.1699
Data Index: 8767190 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7029. Min Range: -4.7029
Max Act: 4.1404. Min Act: -0.1699
Data Index: 5640260 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7029. Min Range: -4.7029
Max Act: 4.0779. Min Act: -0.1698
Data Index: 3724939 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7029. Min Range: -4.7029
Max Act: 4.1091. Min Act: -0.1696
Data Index: 3762180 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7029. Min Range: -4.7029
Max Act: 4.0779. Min Act: -0.1685
Data Index: 5225665 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7029. Min Range: -4.7029
Max Act: 4.0779. Min Act: -0.1688
Data Index: 3724933 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7029. Min Range: -4.7029
Max Act: 4.0779. Min Act: -0.1680
Data Index: 3762190 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7029. Min Range: -4.7029
Max Act: 4.0779. Min Act: -0.1697
Data Index: 2407859 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7029. Min Range: -4.7029
Max Act: 4.0466. Min Act: -0.1700
Data Index: 3762169 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7029. Min Range: -4.7029
Max Act: 4.0466. Min Act: -0.1699
Data Index: 3762173 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7029. Min Range: -4.7029
Max Act: 4.0466. Min Act: -0.1685
Data Index: 3724942 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7029. Min Range: -4.7029
Max Act: 4.0153. Min Act: -0.1653
Data Index: 3762183 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #19