Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1079 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.6012. Min Act: -0.1700
Data Index: 4538131 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.6012. Min Act: -0.1700
Data Index: 7342048 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.5700. Min Act: -0.1700
Data Index: 4650292 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.5387. Min Act: -0.1700
Data Index: 4594267 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.5387. Min Act: -0.1700
Data Index: 5185404 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.5075. Min Act: -0.1700
Data Index: 4161166 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.4450. Min Act: -0.1700
Data Index: 8572135 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.4137. Min Act: -0.1700
Data Index: 6324856 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.4450. Min Act: -0.1700
Data Index: 6618731 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.4137. Min Act: -0.1700
Data Index: 1754853 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.4137. Min Act: -0.1700
Data Index: 1522783 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.4137. Min Act: -0.1700
Data Index: 1318504 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.4137. Min Act: -0.1700
Data Index: 5193420 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.3825. Min Act: -0.1700
Data Index: 5590291 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.3512. Min Act: -0.1700
Data Index: 4099806 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.3512. Min Act: -0.1700
Data Index: 5638336 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.3825. Min Act: -0.1700
Data Index: 7725988 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.3825. Min Act: -0.1700
Data Index: 5142903 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.3825. Min Act: -0.1700
Data Index: 6757791 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.3825. Min Act: -0.1700
Data Index: 3818286 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19