Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2281 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8748. Min Range: -6.8748
Max Act: 6.8748. Min Act: -0.1700
Data Index: 1041779 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8748. Min Range: -6.8748
Max Act: 6.6561. Min Act: -0.1700
Data Index: 8623839 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8748. Min Range: -6.8748
Max Act: 6.5623. Min Act: -0.1700
Data Index: 7594807 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8748. Min Range: -6.8748
Max Act: 6.5623. Min Act: -0.1700
Data Index: 6377334 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8748. Min Range: -6.8748
Max Act: 6.4686. Min Act: -0.1700
Data Index: 5617313 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8748. Min Range: -6.8748
Max Act: 6.4686. Min Act: -0.1700
Data Index: 3356103 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8748. Min Range: -6.8748
Max Act: 6.4061. Min Act: -0.1700
Data Index: 442890 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8748. Min Range: -6.8748
Max Act: 6.4061. Min Act: -0.1700
Data Index: 8557392 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8748. Min Range: -6.8748
Max Act: 6.3436. Min Act: -0.1700
Data Index: 4817244 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8748. Min Range: -6.8748
Max Act: 6.3436. Min Act: -0.1700
Data Index: 1493056 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8748. Min Range: -6.8748
Max Act: 6.3748. Min Act: -0.1700
Data Index: 4732726 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8748. Min Range: -6.8748
Max Act: 6.3436. Min Act: -0.1700
Data Index: 4499014 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8748. Min Range: -6.8748
Max Act: 6.3123. Min Act: -0.1700
Data Index: 6083018 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8748. Min Range: -6.8748
Max Act: 6.3748. Min Act: -0.1700
Data Index: 7301797 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8748. Min Range: -6.8748
Max Act: 6.3123. Min Act: -0.1700
Data Index: 2016369 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8748. Min Range: -6.8748
Max Act: 6.3123. Min Act: -0.1700
Data Index: 134399 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8748. Min Range: -6.8748
Max Act: 6.2811. Min Act: -0.1700
Data Index: 754102 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8748. Min Range: -6.8748
Max Act: 6.2811. Min Act: -0.1700
Data Index: 7679584 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8748. Min Range: -6.8748
Max Act: 6.2498. Min Act: -0.1700
Data Index: 2260840 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8748. Min Range: -6.8748
Max Act: 6.2498. Min Act: -0.1700
Data Index: 1647370 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19