Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1632 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2237. Min Range: -5.2237
Max Act: 5.2237. Min Act: -0.1700
Data Index: 7417375 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2237. Min Range: -5.2237
Max Act: 5.1924. Min Act: -0.1700
Data Index: 2348041 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2237. Min Range: -5.2237
Max Act: 5.1299. Min Act: -0.1700
Data Index: 2752564 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2237. Min Range: -5.2237
Max Act: 5.0987. Min Act: -0.1700
Data Index: 5289680 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2237. Min Range: -5.2237
Max Act: 5.0987. Min Act: -0.1700
Data Index: 1864716 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2237. Min Range: -5.2237
Max Act: 5.0674. Min Act: -0.1700
Data Index: 8399966 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2237. Min Range: -5.2237
Max Act: 5.0987. Min Act: -0.1700
Data Index: 1277803 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2237. Min Range: -5.2237
Max Act: 5.0674. Min Act: -0.1700
Data Index: 5915020 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2237. Min Range: -5.2237
Max Act: 5.0674. Min Act: -0.1699
Data Index: 6788791 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2237. Min Range: -5.2237
Max Act: 5.0674. Min Act: -0.1700
Data Index: 4596170 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2237. Min Range: -5.2237
Max Act: 5.0362. Min Act: -0.1700
Data Index: 6740965 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2237. Min Range: -5.2237
Max Act: 5.0362. Min Act: -0.1700
Data Index: 4996650 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2237. Min Range: -5.2237
Max Act: 5.0049. Min Act: -0.1700
Data Index: 6834722 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2237. Min Range: -5.2237
Max Act: 5.0049. Min Act: -0.1700
Data Index: 6513606 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2237. Min Range: -5.2237
Max Act: 4.9737. Min Act: -0.1700
Data Index: 8183123 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2237. Min Range: -5.2237
Max Act: 4.9737. Min Act: -0.1700
Data Index: 3106709 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2237. Min Range: -5.2237
Max Act: 4.9424. Min Act: -0.1700
Data Index: 2503031 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2237. Min Range: -5.2237
Max Act: 4.9424. Min Act: -0.1700
Data Index: 7956666 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2237. Min Range: -5.2237
Max Act: 4.8799. Min Act: -0.1700
Data Index: 3979140 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2237. Min Range: -5.2237
Max Act: 4.8799. Min Act: -0.1700
Data Index: 4788935 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19