Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2625 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1648. Min Range: -5.1648
Max Act: 5.1648. Min Act: -0.1700
Data Index: 1622962 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1648. Min Range: -5.1648
Max Act: 5.1648. Min Act: -0.1700
Data Index: 1036065 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.8836. Min Act: -0.1700
Data Index: 713703 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.8211. Min Act: -0.1700
Data Index: 5886253 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.8211. Min Act: -0.1700
Data Index: 7338461 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.7898. Min Act: -0.1700
Data Index: 3232088 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.7586. Min Act: -0.1700
Data Index: 1753913 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.7586. Min Act: -0.1700
Data Index: 1147322 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.6961. Min Act: -0.1700
Data Index: 902963 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.7273. Min Act: -0.1700
Data Index: 1931650 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.6336. Min Act: -0.1700
Data Index: 4797911 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.6648. Min Act: -0.1700
Data Index: 5144689 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.6336. Min Act: -0.1700
Data Index: 2261332 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.6336. Min Act: -0.1700
Data Index: 1842503 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.6336. Min Act: -0.1700
Data Index: 8486078 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.6336. Min Act: -0.1700
Data Index: 1765678 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.6023. Min Act: -0.1700
Data Index: 7741279 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.6336. Min Act: -0.1700
Data Index: 286585 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.6023. Min Act: -0.1700
Data Index: 6647905 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1648. Min Range: -5.1648
Max Act: 4.6023. Min Act: -0.1700
Data Index: 973646 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19