Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1932 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5497. Min Range: -5.5497
Max Act: 5.5497. Min Act: -0.1700
Data Index: 6116744 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5497. Min Range: -5.5497
Max Act: 5.2372. Min Act: -0.1700
Data Index: 4586810 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5497. Min Range: -5.5497
Max Act: 5.2372. Min Act: -0.1700
Data Index: 7241565 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5497. Min Range: -5.5497
Max Act: 5.1435. Min Act: -0.1700
Data Index: 6264762 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5497. Min Range: -5.5497
Max Act: 5.1747. Min Act: -0.1700
Data Index: 6766280 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5497. Min Range: -5.5497
Max Act: 5.1435. Min Act: -0.1700
Data Index: 8410145 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5497. Min Range: -5.5497
Max Act: 5.1122. Min Act: -0.1700
Data Index: 3802980 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5497. Min Range: -5.5497
Max Act: 5.1435. Min Act: -0.1700
Data Index: 1284052 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5497. Min Range: -5.5497
Max Act: 5.1122. Min Act: -0.1700
Data Index: 1662896 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5497. Min Range: -5.5497
Max Act: 5.0497. Min Act: -0.1700
Data Index: 956184 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5497. Min Range: -5.5497
Max Act: 5.0810. Min Act: -0.1700
Data Index: 352071 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5497. Min Range: -5.5497
Max Act: 5.0185. Min Act: -0.1700
Data Index: 466042 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5497. Min Range: -5.5497
Max Act: 4.9872. Min Act: -0.1700
Data Index: 251503 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5497. Min Range: -5.5497
Max Act: 4.9560. Min Act: -0.1700
Data Index: 8133735 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5497. Min Range: -5.5497
Max Act: 4.9560. Min Act: -0.1700
Data Index: 1683170 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5497. Min Range: -5.5497
Max Act: 4.9560. Min Act: -0.1700
Data Index: 8763110 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5497. Min Range: -5.5497
Max Act: 4.9560. Min Act: -0.1700
Data Index: 7039495 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5497. Min Range: -5.5497
Max Act: 4.9560. Min Act: -0.1700
Data Index: 8323603 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5497. Min Range: -5.5497
Max Act: 4.9560. Min Act: -0.1700
Data Index: 1898552 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5497. Min Range: -5.5497
Max Act: 4.8935. Min Act: -0.1700
Data Index: 3373550 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19