Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6254 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6490. Min Range: -7.6490
Max Act: 7.6490. Min Act: -0.1700
Data Index: 4061538 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6490. Min Range: -7.6490
Max Act: 7.3365. Min Act: -0.1700
Data Index: 2085346 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6490. Min Range: -7.6490
Max Act: 7.2740. Min Act: -0.1700
Data Index: 5235064 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6490. Min Range: -7.6490
Max Act: 7.2115. Min Act: -0.1700
Data Index: 2684983 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6490. Min Range: -7.6490
Max Act: 7.1802. Min Act: -0.1700
Data Index: 5690262 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6490. Min Range: -7.6490
Max Act: 7.1802. Min Act: -0.1700
Data Index: 5961453 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6490. Min Range: -7.6490
Max Act: 7.1177. Min Act: -0.1700
Data Index: 1043812 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6490. Min Range: -7.6490
Max Act: 7.0865. Min Act: -0.1700
Data Index: 6854544 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6490. Min Range: -7.6490
Max Act: 7.0865. Min Act: -0.1700
Data Index: 1220169 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6490. Min Range: -7.6490
Max Act: 7.0552. Min Act: -0.1700
Data Index: 7473092 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6490. Min Range: -7.6490
Max Act: 6.9615. Min Act: -0.1700
Data Index: 892511 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6490. Min Range: -7.6490
Max Act: 6.9927. Min Act: -0.1700
Data Index: 7743016 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6490. Min Range: -7.6490
Max Act: 6.9302. Min Act: -0.1700
Data Index: 4147670 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6490. Min Range: -7.6490
Max Act: 6.9302. Min Act: -0.1700
Data Index: 8661366 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6490. Min Range: -7.6490
Max Act: 6.9302. Min Act: -0.1700
Data Index: 1695037 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6490. Min Range: -7.6490
Max Act: 6.9302. Min Act: -0.1700
Data Index: 6081581 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6490. Min Range: -7.6490
Max Act: 6.8990. Min Act: -0.1700
Data Index: 6095951 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6490. Min Range: -7.6490
Max Act: 6.8990. Min Act: -0.1700
Data Index: 2130839 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6490. Min Range: -7.6490
Max Act: 6.9302. Min Act: -0.1700
Data Index: 8691371 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6490. Min Range: -7.6490
Max Act: 6.8677. Min Act: -0.1700
Data Index: 3088143 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19