Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5097 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6897. Min Range: -5.6897
Max Act: 5.6897. Min Act: -0.1700
Data Index: 6143328 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6897. Min Range: -5.6897
Max Act: 5.6585. Min Act: -0.1700
Data Index: 1708669 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6897. Min Range: -5.6897
Max Act: 5.5960. Min Act: -0.1700
Data Index: 2175529 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6897. Min Range: -5.6897
Max Act: 5.5960. Min Act: -0.1700
Data Index: 5490218 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6897. Min Range: -5.6897
Max Act: 5.5960. Min Act: -0.1700
Data Index: 5777640 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6897. Min Range: -5.6897
Max Act: 5.5960. Min Act: -0.1700
Data Index: 1545154 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6897. Min Range: -5.6897
Max Act: 5.5960. Min Act: -0.1700
Data Index: 2354821 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6897. Min Range: -5.6897
Max Act: 5.5960. Min Act: -0.1700
Data Index: 1103646 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6897. Min Range: -5.6897
Max Act: 5.5960. Min Act: -0.1700
Data Index: 5226465 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6897. Min Range: -5.6897
Max Act: 5.5647. Min Act: -0.1700
Data Index: 8768753 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6897. Min Range: -5.6897
Max Act: 5.5647. Min Act: -0.1700
Data Index: 2273979 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6897. Min Range: -5.6897
Max Act: 5.5647. Min Act: -0.1700
Data Index: 8688228 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6897. Min Range: -5.6897
Max Act: 5.5647. Min Act: -0.1700
Data Index: 6934155 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6897. Min Range: -5.6897
Max Act: 5.5647. Min Act: -0.1700
Data Index: 1580593 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6897. Min Range: -5.6897
Max Act: 5.5647. Min Act: -0.1700
Data Index: 1389043 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6897. Min Range: -5.6897
Max Act: 5.5335. Min Act: -0.1700
Data Index: 651520 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6897. Min Range: -5.6897
Max Act: 5.5335. Min Act: -0.1700
Data Index: 238477 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6897. Min Range: -5.6897
Max Act: 5.5647. Min Act: -0.1700
Data Index: 2708568 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6897. Min Range: -5.6897
Max Act: 5.5335. Min Act: -0.1700
Data Index: 2895063 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6897. Min Range: -5.6897
Max Act: 5.5335. Min Act: -0.1700
Data Index: 1839209 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19