Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3778 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1694. Min Range: -6.1694
Max Act: 6.1694. Min Act: -0.1700
Data Index: 4083406 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1694. Min Range: -6.1694
Max Act: 6.0756. Min Act: -0.1700
Data Index: 4849206 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.9506. Min Act: -0.1700
Data Index: 5648113 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.8256. Min Act: -0.1700
Data Index: 7964635 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.8569. Min Act: -0.1700
Data Index: 1436144 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.8256. Min Act: -0.1700
Data Index: 571670 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.8569. Min Act: -0.1700
Data Index: 1292938 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.8256. Min Act: -0.1700
Data Index: 2620063 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.7944. Min Act: -0.1700
Data Index: 8514516 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.8256. Min Act: -0.1700
Data Index: 846561 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.7944. Min Act: -0.1700
Data Index: 1583420 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.7631. Min Act: -0.1700
Data Index: 4122616 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.7319. Min Act: -0.1700
Data Index: 4892029 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.7319. Min Act: -0.1700
Data Index: 2174795 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.7631. Min Act: -0.1700
Data Index: 1555394 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.7319. Min Act: -0.1700
Data Index: 7941599 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.7006. Min Act: -0.1700
Data Index: 5414693 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.7006. Min Act: -0.1700
Data Index: 4674672 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.7319. Min Act: -0.1700
Data Index: 4295035 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.7319. Min Act: -0.1700
Data Index: 2034046 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19