Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6376 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.5340. Min Act: -0.1700
Data Index: 2065632 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.5340. Min Act: -0.1700
Data Index: 7977919 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.5027. Min Act: -0.1700
Data Index: 3341676 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.4402. Min Act: -0.1700
Data Index: 8299713 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.4402. Min Act: -0.1700
Data Index: 5981629 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.4090. Min Act: -0.1700
Data Index: 3668607 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.3777. Min Act: -0.1700
Data Index: 1481960 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.3465. Min Act: -0.1700
Data Index: 7015011 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.3465. Min Act: -0.1700
Data Index: 2438820 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.3465. Min Act: -0.1700
Data Index: 2528303 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.3465. Min Act: -0.1700
Data Index: 2167531 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.3465. Min Act: -0.1700
Data Index: 1381962 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.3152. Min Act: -0.1700
Data Index: 2694428 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.2840. Min Act: -0.1700
Data Index: 6343208 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.3152. Min Act: -0.1700
Data Index: 6154089 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.3152. Min Act: -0.1700
Data Index: 3196522 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.2840. Min Act: -0.1700
Data Index: 4637750 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.3152. Min Act: -0.1700
Data Index: 3019702 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.3152. Min Act: -0.1700
Data Index: 4765695 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.2840. Min Act: -0.1700
Data Index: 3006229 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #19