Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5352 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.9288. Min Act: -0.1700
Data Index: 5485348 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.8038. Min Act: -0.1700
Data Index: 6855539 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.6475. Min Act: -0.1700
Data Index: 244367 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.6475. Min Act: -0.1700
Data Index: 270462 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.5850. Min Act: -0.1700
Data Index: 8363764 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.5538. Min Act: -0.1700
Data Index: 405600 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.5538. Min Act: -0.1700
Data Index: 8107639 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.5538. Min Act: -0.1700
Data Index: 7080242 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.5225. Min Act: -0.1700
Data Index: 5808538 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.5225. Min Act: -0.1700
Data Index: 3472808 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.4913. Min Act: -0.1700
Data Index: 4927468 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.5225. Min Act: -0.1700
Data Index: 4288938 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.5225. Min Act: -0.1700
Data Index: 8570734 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.4913. Min Act: -0.1700
Data Index: 2876721 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.4600. Min Act: -0.1700
Data Index: 942297 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.4600. Min Act: -0.1700
Data Index: 3368670 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.4600. Min Act: -0.1700
Data Index: 703610 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.4600. Min Act: -0.1700
Data Index: 4706383 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.4600. Min Act: -0.1700
Data Index: 3969384 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.4600. Min Act: -0.1700
Data Index: 8171167 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19