Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4850 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6975. Min Range: -5.6975
Max Act: 5.6975. Min Act: -0.1700
Data Index: 5349198 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6975. Min Range: -5.6975
Max Act: 5.6662. Min Act: -0.1700
Data Index: 1285965 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6975. Min Range: -5.6975
Max Act: 5.6662. Min Act: -0.1700
Data Index: 8277368 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6975. Min Range: -5.6975
Max Act: 5.5725. Min Act: -0.1700
Data Index: 186642 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6975. Min Range: -5.6975
Max Act: 5.5725. Min Act: -0.1700
Data Index: 8517284 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6975. Min Range: -5.6975
Max Act: 5.5412. Min Act: -0.1700
Data Index: 6338087 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6975. Min Range: -5.6975
Max Act: 5.5100. Min Act: -0.1700
Data Index: 3077125 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6975. Min Range: -5.6975
Max Act: 5.4475. Min Act: -0.1700
Data Index: 1167046 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6975. Min Range: -5.6975
Max Act: 5.4787. Min Act: -0.1700
Data Index: 2751792 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6975. Min Range: -5.6975
Max Act: 5.4475. Min Act: -0.1700
Data Index: 4858782 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6975. Min Range: -5.6975
Max Act: 5.4475. Min Act: -0.1700
Data Index: 4074500 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6975. Min Range: -5.6975
Max Act: 5.4475. Min Act: -0.1700
Data Index: 186647 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6975. Min Range: -5.6975
Max Act: 5.4787. Min Act: -0.1700
Data Index: 5418205 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6975. Min Range: -5.6975
Max Act: 5.4475. Min Act: -0.1700
Data Index: 1890522 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6975. Min Range: -5.6975
Max Act: 5.4162. Min Act: -0.1700
Data Index: 186645 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6975. Min Range: -5.6975
Max Act: 5.4162. Min Act: -0.1700
Data Index: 1884108 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6975. Min Range: -5.6975
Max Act: 5.4162. Min Act: -0.1700
Data Index: 1056651 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6975. Min Range: -5.6975
Max Act: 5.3850. Min Act: -0.1700
Data Index: 1666368 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6975. Min Range: -5.6975
Max Act: 5.3850. Min Act: -0.1700
Data Index: 5150761 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6975. Min Range: -5.6975
Max Act: 5.3850. Min Act: -0.1700
Data Index: 7610806 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19