Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4865 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8030. Min Range: -8.8030
Max Act: 8.8030. Min Act: -0.1700
Data Index: 4307249 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8030. Min Range: -8.8030
Max Act: 8.6155. Min Act: -0.1700
Data Index: 4527625 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8030. Min Range: -8.8030
Max Act: 8.4905. Min Act: -0.1700
Data Index: 6688648 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8030. Min Range: -8.8030
Max Act: 8.4280. Min Act: -0.1700
Data Index: 6436655 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8030. Min Range: -8.8030
Max Act: 8.2405. Min Act: -0.1700
Data Index: 5746467 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8030. Min Range: -8.8030
Max Act: 8.3030. Min Act: -0.1700
Data Index: 8394063 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8030. Min Range: -8.8030
Max Act: 8.1780. Min Act: -0.1700
Data Index: 2512888 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8030. Min Range: -8.8030
Max Act: 8.2405. Min Act: -0.1700
Data Index: 2768172 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8030. Min Range: -8.8030
Max Act: 8.2405. Min Act: -0.1700
Data Index: 6394492 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8030. Min Range: -8.8030
Max Act: 8.2405. Min Act: -0.1700
Data Index: 6866415 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8030. Min Range: -8.8030
Max Act: 8.2405. Min Act: -0.1700
Data Index: 6053217 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8030. Min Range: -8.8030
Max Act: 8.2405. Min Act: -0.1700
Data Index: 6491940 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8030. Min Range: -8.8030
Max Act: 8.2405. Min Act: -0.1700
Data Index: 8360370 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8030. Min Range: -8.8030
Max Act: 8.1780. Min Act: -0.1700
Data Index: 465972 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8030. Min Range: -8.8030
Max Act: 8.1780. Min Act: -0.1700
Data Index: 8035708 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8030. Min Range: -8.8030
Max Act: 8.1780. Min Act: -0.1700
Data Index: 8035707 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8030. Min Range: -8.8030
Max Act: 8.0530. Min Act: -0.1700
Data Index: 2789292 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8030. Min Range: -8.8030
Max Act: 8.0530. Min Act: -0.1700
Data Index: 5489432 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8030. Min Range: -8.8030
Max Act: 8.0530. Min Act: -0.1700
Data Index: 2239006 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8030. Min Range: -8.8030
Max Act: 8.0530. Min Act: -0.1700
Data Index: 6569188 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19