Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1187 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4072. Min Range: -7.4072
Max Act: 7.4072. Min Act: -0.1700
Data Index: 1555466 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4072. Min Range: -7.4072
Max Act: 7.0322. Min Act: -0.1700
Data Index: 4707876 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4072. Min Range: -7.4072
Max Act: 6.8447. Min Act: -0.1700
Data Index: 4534405 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4072. Min Range: -7.4072
Max Act: 6.8134. Min Act: -0.1700
Data Index: 1542535 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4072. Min Range: -7.4072
Max Act: 6.7822. Min Act: -0.1700
Data Index: 3814143 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4072. Min Range: -7.4072
Max Act: 6.7509. Min Act: -0.1700
Data Index: 1147813 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4072. Min Range: -7.4072
Max Act: 6.6884. Min Act: -0.1700
Data Index: 4181621 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4072. Min Range: -7.4072
Max Act: 6.7509. Min Act: -0.1700
Data Index: 4603601 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4072. Min Range: -7.4072
Max Act: 6.6884. Min Act: -0.1700
Data Index: 3404445 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4072. Min Range: -7.4072
Max Act: 6.6259. Min Act: -0.1700
Data Index: 6533834 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4072. Min Range: -7.4072
Max Act: 6.6572. Min Act: -0.1700
Data Index: 2386711 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4072. Min Range: -7.4072
Max Act: 6.5947. Min Act: -0.1700
Data Index: 4544261 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4072. Min Range: -7.4072
Max Act: 6.5947. Min Act: -0.1700
Data Index: 3829612 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4072. Min Range: -7.4072
Max Act: 6.5947. Min Act: -0.1700
Data Index: 1598490 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4072. Min Range: -7.4072
Max Act: 6.5634. Min Act: -0.1700
Data Index: 654662 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4072. Min Range: -7.4072
Max Act: 6.5322. Min Act: -0.1700
Data Index: 299937 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4072. Min Range: -7.4072
Max Act: 6.5322. Min Act: -0.1700
Data Index: 1736138 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4072. Min Range: -7.4072
Max Act: 6.5322. Min Act: -0.1700
Data Index: 515899 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4072. Min Range: -7.4072
Max Act: 6.5009. Min Act: -0.1700
Data Index: 2099616 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4072. Min Range: -7.4072
Max Act: 6.5009. Min Act: -0.1700
Data Index: 1378277 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19