Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3101 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2747. Min Range: -6.2747
Max Act: 6.2747. Min Act: -0.1700
Data Index: 7564939 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2747. Min Range: -6.2747
Max Act: 6.1184. Min Act: -0.1700
Data Index: 1598045 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2747. Min Range: -6.2747
Max Act: 6.0872. Min Act: -0.1700
Data Index: 4540216 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2747. Min Range: -6.2747
Max Act: 6.0247. Min Act: -0.1700
Data Index: 22662 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2747. Min Range: -6.2747
Max Act: 5.9622. Min Act: -0.1700
Data Index: 5454414 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2747. Min Range: -6.2747
Max Act: 6.0247. Min Act: -0.1700
Data Index: 7003542 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2747. Min Range: -6.2747
Max Act: 5.9622. Min Act: -0.1700
Data Index: 5602718 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2747. Min Range: -6.2747
Max Act: 5.9622. Min Act: -0.1700
Data Index: 4232509 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2747. Min Range: -6.2747
Max Act: 5.9622. Min Act: -0.1700
Data Index: 3262544 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2747. Min Range: -6.2747
Max Act: 5.9309. Min Act: -0.1700
Data Index: 4581285 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2747. Min Range: -6.2747
Max Act: 5.9309. Min Act: -0.1700
Data Index: 298403 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2747. Min Range: -6.2747
Max Act: 5.9309. Min Act: -0.1700
Data Index: 372523 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2747. Min Range: -6.2747
Max Act: 5.8997. Min Act: -0.1700
Data Index: 6274073 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2747. Min Range: -6.2747
Max Act: 5.8997. Min Act: -0.1700
Data Index: 3490345 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2747. Min Range: -6.2747
Max Act: 5.9309. Min Act: -0.1700
Data Index: 1976342 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2747. Min Range: -6.2747
Max Act: 5.8997. Min Act: -0.1700
Data Index: 846890 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2747. Min Range: -6.2747
Max Act: 5.8997. Min Act: -0.1700
Data Index: 3756945 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2747. Min Range: -6.2747
Max Act: 5.8997. Min Act: -0.1700
Data Index: 8502337 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2747. Min Range: -6.2747
Max Act: 5.8997. Min Act: -0.1700
Data Index: 102521 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2747. Min Range: -6.2747
Max Act: 5.9309. Min Act: -0.1700
Data Index: 1565170 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19