Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5483 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4282. Min Range: -3.4282
Max Act: 3.4282. Min Act: -0.1700
Data Index: 3362692 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4282. Min Range: -3.4282
Max Act: 3.4282. Min Act: -0.1700
Data Index: 3704583 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4282. Min Range: -3.4282
Max Act: 3.3968. Min Act: -0.1700
Data Index: 1559879 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4282. Min Range: -3.4282
Max Act: 3.3498. Min Act: -0.1700
Data Index: 797378 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4282. Min Range: -3.4282
Max Act: 3.3341. Min Act: -0.1700
Data Index: 1506545 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4282. Min Range: -3.4282
Max Act: 3.2713. Min Act: -0.1700
Data Index: 5316313 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4282. Min Range: -3.4282
Max Act: 3.2399. Min Act: -0.1700
Data Index: 6081305 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4282. Min Range: -3.4282
Max Act: 3.2399. Min Act: -0.1700
Data Index: 327208 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4282. Min Range: -3.4282
Max Act: 3.2084. Min Act: -0.1700
Data Index: 6943722 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4282. Min Range: -3.4282
Max Act: 3.1927. Min Act: -0.1700
Data Index: 4447113 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4282. Min Range: -3.4282
Max Act: 3.2084. Min Act: -0.1700
Data Index: 3563973 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4282. Min Range: -3.4282
Max Act: 3.2084. Min Act: -0.1700
Data Index: 3110672 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4282. Min Range: -3.4282
Max Act: 3.2084. Min Act: -0.1700
Data Index: 1333228 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4282. Min Range: -3.4282
Max Act: 3.1927. Min Act: -0.1700
Data Index: 2740157 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4282. Min Range: -3.4282
Max Act: 3.1770. Min Act: -0.1700
Data Index: 2051048 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4282. Min Range: -3.4282
Max Act: 3.1927. Min Act: -0.1700
Data Index: 405120 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4282. Min Range: -3.4282
Max Act: 3.1770. Min Act: -0.1700
Data Index: 7285440 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4282. Min Range: -3.4282
Max Act: 3.1770. Min Act: -0.1700
Data Index: 1254839 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4282. Min Range: -3.4282
Max Act: 3.1612. Min Act: -0.1700
Data Index: 374445 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4282. Min Range: -3.4282
Max Act: 3.1455. Min Act: -0.1700
Data Index: 5527463 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19