Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5410 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3207. Min Range: -2.3207
Max Act: 2.3207. Min Act: -0.1700
Data Index: 3018139 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3207. Min Range: -2.3207
Max Act: 2.2878. Min Act: -0.1700
Data Index: 3877401 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3207. Min Range: -2.3207
Max Act: 2.2548. Min Act: -0.1700
Data Index: 3728712 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3207. Min Range: -2.3207
Max Act: 2.2713. Min Act: -0.1700
Data Index: 5582262 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3207. Min Range: -2.3207
Max Act: 2.2051. Min Act: -0.1700
Data Index: 8454170 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3207. Min Range: -2.3207
Max Act: 2.1719. Min Act: -0.1700
Data Index: 606076 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3207. Min Range: -2.3207
Max Act: 2.1885. Min Act: -0.1700
Data Index: 1437506 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3207. Min Range: -2.3207
Max Act: 2.1719. Min Act: -0.1700
Data Index: 6922771 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3207. Min Range: -2.3207
Max Act: 2.1885. Min Act: -0.1700
Data Index: 6609142 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3207. Min Range: -2.3207
Max Act: 2.1719. Min Act: -0.1700
Data Index: 6107618 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3207. Min Range: -2.3207
Max Act: 2.1719. Min Act: -0.1700
Data Index: 2049267 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3207. Min Range: -2.3207
Max Act: 2.1719. Min Act: -0.1700
Data Index: 3996822 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3207. Min Range: -2.3207
Max Act: 2.1885. Min Act: -0.1700
Data Index: 3478641 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3207. Min Range: -2.3207
Max Act: 2.1386. Min Act: -0.1700
Data Index: 4253920 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3207. Min Range: -2.3207
Max Act: 2.1553. Min Act: -0.1700
Data Index: 7633106 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3207. Min Range: -2.3207
Max Act: 2.1553. Min Act: -0.1700
Data Index: 2612695 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3207. Min Range: -2.3207
Max Act: 2.1553. Min Act: -0.1700
Data Index: 8458197 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3207. Min Range: -2.3207
Max Act: 2.1553. Min Act: -0.1700
Data Index: 8753801 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3207. Min Range: -2.3207
Max Act: 2.1386. Min Act: -0.1700
Data Index: 1288458 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3207. Min Range: -2.3207
Max Act: 2.1553. Min Act: -0.1700
Data Index: 6221147 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19