Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 543 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1559. Min Range: -8.1559
Max Act: 8.1559. Min Act: -0.1700
Data Index: 6014505 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1559. Min Range: -8.1559
Max Act: 7.5622. Min Act: -0.1700
Data Index: 5254627 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1559. Min Range: -8.1559
Max Act: 7.4059. Min Act: -0.1700
Data Index: 5895504 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1559. Min Range: -8.1559
Max Act: 7.1872. Min Act: -0.1700
Data Index: 8542846 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1559. Min Range: -8.1559
Max Act: 7.0934. Min Act: -0.1700
Data Index: 6028308 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1559. Min Range: -8.1559
Max Act: 6.9997. Min Act: -0.1700
Data Index: 468217 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1559. Min Range: -8.1559
Max Act: 6.9059. Min Act: -0.1700
Data Index: 2942048 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1559. Min Range: -8.1559
Max Act: 6.9059. Min Act: -0.1700
Data Index: 2060252 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1559. Min Range: -8.1559
Max Act: 6.8747. Min Act: -0.1700
Data Index: 171269 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1559. Min Range: -8.1559
Max Act: 6.9059. Min Act: -0.1700
Data Index: 4210700 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1559. Min Range: -8.1559
Max Act: 6.8747. Min Act: -0.1700
Data Index: 7105372 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1559. Min Range: -8.1559
Max Act: 6.8122. Min Act: -0.1700
Data Index: 2769018 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1559. Min Range: -8.1559
Max Act: 6.8122. Min Act: -0.1700
Data Index: 2153461 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1559. Min Range: -8.1559
Max Act: 6.7809. Min Act: -0.1700
Data Index: 6864087 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1559. Min Range: -8.1559
Max Act: 6.7497. Min Act: -0.1700
Data Index: 141944 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1559. Min Range: -8.1559
Max Act: 6.7809. Min Act: -0.1700
Data Index: 6448772 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1559. Min Range: -8.1559
Max Act: 6.7497. Min Act: -0.1700
Data Index: 5997669 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1559. Min Range: -8.1559
Max Act: 6.7497. Min Act: -0.1700
Data Index: 264361 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1559. Min Range: -8.1559
Max Act: 6.7497. Min Act: -0.1700
Data Index: 7812451 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1559. Min Range: -8.1559
Max Act: 6.7497. Min Act: -0.1700
Data Index: 7583818 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19