Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2839 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0575. Min Range: -8.0575
Max Act: 8.0575. Min Act: -0.1700
Data Index: 4073646 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.8700. Min Act: -0.1700
Data Index: 2133646 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.4638. Min Act: -0.1700
Data Index: 3605642 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.4638. Min Act: -0.1700
Data Index: 2296448 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.4325. Min Act: -0.1700
Data Index: 3170652 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.4013. Min Act: -0.1700
Data Index: 292697 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.4013. Min Act: -0.1700
Data Index: 1311239 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.3700. Min Act: -0.1700
Data Index: 2747915 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.2450. Min Act: -0.1700
Data Index: 1299440 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.2450. Min Act: -0.1700
Data Index: 2357171 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.1825. Min Act: -0.1700
Data Index: 807268 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.0888. Min Act: -0.1700
Data Index: 428733 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.0888. Min Act: -0.1700
Data Index: 7642490 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.0888. Min Act: -0.1700
Data Index: 3734600 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.0888. Min Act: -0.1700
Data Index: 4678410 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.0263. Min Act: -0.1700
Data Index: 395203 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.0263. Min Act: -0.1700
Data Index: 1845822 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0575. Min Range: -8.0575
Max Act: 6.9950. Min Act: -0.1700
Data Index: 8271606 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.0263. Min Act: -0.1700
Data Index: 416594 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0575. Min Range: -8.0575
Max Act: 6.9950. Min Act: -0.1700
Data Index: 7502666 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #19