Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2564 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1556. Min Range: -2.1556
Max Act: 2.1556. Min Act: -0.1700
Data Index: 5036861 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1556. Min Range: -2.1556
Max Act: 2.0552. Min Act: -0.1700
Data Index: 3644202 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1556. Min Range: -2.1556
Max Act: 2.0384. Min Act: -0.1700
Data Index: 2237304 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1556. Min Range: -2.1556
Max Act: 2.0384. Min Act: -0.1700
Data Index: 3644198 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1556. Min Range: -2.1556
Max Act: 2.0047. Min Act: -0.1700
Data Index: 3439335 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1556. Min Range: -2.1556
Max Act: 2.0047. Min Act: -0.1700
Data Index: 8572284 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1556. Min Range: -2.1556
Max Act: 2.0047. Min Act: -0.1699
Data Index: 8665581 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1556. Min Range: -2.1556
Max Act: 2.0047. Min Act: -0.1700
Data Index: 8689421 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1556. Min Range: -2.1556
Max Act: 2.0047. Min Act: -0.1700
Data Index: 2059976 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1556. Min Range: -2.1556
Max Act: 1.9708. Min Act: -0.1700
Data Index: 2457671 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1556. Min Range: -2.1556
Max Act: 1.9708. Min Act: -0.1700
Data Index: 4125894 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1556. Min Range: -2.1556
Max Act: 1.9878. Min Act: -0.1700
Data Index: 8294567 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1556. Min Range: -2.1556
Max Act: 1.9708. Min Act: -0.1700
Data Index: 2179022 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1556. Min Range: -2.1556
Max Act: 1.9708. Min Act: -0.1700
Data Index: 3020167 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1556. Min Range: -2.1556
Max Act: 1.9708. Min Act: -0.1699
Data Index: 1630261 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1556. Min Range: -2.1556
Max Act: 1.9708. Min Act: -0.1700
Data Index: 5890645 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1556. Min Range: -2.1556
Max Act: 1.9708. Min Act: -0.1700
Data Index: 1160500 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1556. Min Range: -2.1556
Max Act: 1.9708. Min Act: -0.1700
Data Index: 962999 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1556. Min Range: -2.1556
Max Act: 1.9708. Min Act: -0.1700
Data Index: 4477034 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1556. Min Range: -2.1556
Max Act: 1.9539. Min Act: -0.1700
Data Index: 8605275 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #19