Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3940 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6419. Min Range: -3.6419
Max Act: 3.6419. Min Act: -0.1700
Data Index: 4297218 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6419. Min Range: -3.6419
Max Act: 3.5167. Min Act: -0.1700
Data Index: 29256 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6419. Min Range: -3.6419
Max Act: 3.5010. Min Act: -0.1700
Data Index: 3201683 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6419. Min Range: -3.6419
Max Act: 3.5167. Min Act: -0.1700
Data Index: 592698 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6419. Min Range: -3.6419
Max Act: 3.5010. Min Act: -0.1700
Data Index: 1353002 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6419. Min Range: -3.6419
Max Act: 3.5010. Min Act: -0.1700
Data Index: 4480670 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6419. Min Range: -3.6419
Max Act: 3.5010. Min Act: -0.1700
Data Index: 5865160 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6419. Min Range: -3.6419
Max Act: 3.4697. Min Act: -0.1700
Data Index: 1126678 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6419. Min Range: -3.6419
Max Act: 3.4540. Min Act: -0.1700
Data Index: 7747544 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6419. Min Range: -3.6419
Max Act: 3.4540. Min Act: -0.1700
Data Index: 1931417 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6419. Min Range: -3.6419
Max Act: 3.4540. Min Act: -0.1700
Data Index: 4610162 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6419. Min Range: -3.6419
Max Act: 3.4540. Min Act: -0.1700
Data Index: 5200266 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6419. Min Range: -3.6419
Max Act: 3.4383. Min Act: -0.1700
Data Index: 5615648 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6419. Min Range: -3.6419
Max Act: 3.4383. Min Act: -0.1700
Data Index: 2021413 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6419. Min Range: -3.6419
Max Act: 3.4227. Min Act: -0.1700
Data Index: 2866199 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6419. Min Range: -3.6419
Max Act: 3.4227. Min Act: -0.1700
Data Index: 2554245 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6419. Min Range: -3.6419
Max Act: 3.4227. Min Act: -0.1700
Data Index: 5111146 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6419. Min Range: -3.6419
Max Act: 3.4383. Min Act: -0.1700
Data Index: 3350999 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6419. Min Range: -3.6419
Max Act: 3.4070. Min Act: -0.1700
Data Index: 1283380 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6419. Min Range: -3.6419
Max Act: 3.4070. Min Act: -0.1700
Data Index: 8065358 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19