Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2963 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5851. Min Range: -5.5851
Max Act: 5.5851. Min Act: -0.1700
Data Index: 4757266 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5851. Min Range: -5.5851
Max Act: 5.4601. Min Act: -0.1700
Data Index: 7977117 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5851. Min Range: -5.5851
Max Act: 5.3351. Min Act: -0.1700
Data Index: 3848690 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5851. Min Range: -5.5851
Max Act: 5.3351. Min Act: -0.1700
Data Index: 1682207 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5851. Min Range: -5.5851
Max Act: 5.3039. Min Act: -0.1700
Data Index: 1281427 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5851. Min Range: -5.5851
Max Act: 5.3351. Min Act: -0.1700
Data Index: 5254517 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5851. Min Range: -5.5851
Max Act: 5.2726. Min Act: -0.1700
Data Index: 7408731 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5851. Min Range: -5.5851
Max Act: 5.2726. Min Act: -0.1700
Data Index: 7159622 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5851. Min Range: -5.5851
Max Act: 5.2726. Min Act: -0.1700
Data Index: 403212 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5851. Min Range: -5.5851
Max Act: 5.2414. Min Act: -0.1700
Data Index: 832248 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5851. Min Range: -5.5851
Max Act: 5.2414. Min Act: -0.1700
Data Index: 6450354 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5851. Min Range: -5.5851
Max Act: 5.2414. Min Act: -0.1700
Data Index: 5831477 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5851. Min Range: -5.5851
Max Act: 5.1789. Min Act: -0.1700
Data Index: 5425527 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5851. Min Range: -5.5851
Max Act: 5.2101. Min Act: -0.1700
Data Index: 5598779 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5851. Min Range: -5.5851
Max Act: 5.2101. Min Act: -0.1700
Data Index: 2483607 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5851. Min Range: -5.5851
Max Act: 5.2101. Min Act: -0.1700
Data Index: 5909107 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5851. Min Range: -5.5851
Max Act: 5.1789. Min Act: -0.1700
Data Index: 5357807 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5851. Min Range: -5.5851
Max Act: 5.1789. Min Act: -0.1700
Data Index: 3851660 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5851. Min Range: -5.5851
Max Act: 5.1789. Min Act: -0.1700
Data Index: 5071994 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5851. Min Range: -5.5851
Max Act: 5.1789. Min Act: -0.1700
Data Index: 2683022 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19