Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2342 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5487. Min Range: -5.5487
Max Act: 5.5487. Min Act: -0.1700
Data Index: 4870195 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5487. Min Range: -5.5487
Max Act: 5.4237. Min Act: -0.1700
Data Index: 3218636 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5487. Min Range: -5.5487
Max Act: 5.3925. Min Act: -0.1700
Data Index: 3190696 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5487. Min Range: -5.5487
Max Act: 5.2362. Min Act: -0.1700
Data Index: 8147773 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5487. Min Range: -5.5487
Max Act: 5.1425. Min Act: -0.1700
Data Index: 1240561 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5487. Min Range: -5.5487
Max Act: 5.0175. Min Act: -0.1700
Data Index: 7136153 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5487. Min Range: -5.5487
Max Act: 4.9237. Min Act: -0.1700
Data Index: 2066243 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5487. Min Range: -5.5487
Max Act: 4.7987. Min Act: -0.1700
Data Index: 3739547 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5487. Min Range: -5.5487
Max Act: 4.8300. Min Act: -0.1700
Data Index: 6297751 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5487. Min Range: -5.5487
Max Act: 4.7987. Min Act: -0.1700
Data Index: 3739548 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5487. Min Range: -5.5487
Max Act: 4.7987. Min Act: -0.1700
Data Index: 7903882 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5487. Min Range: -5.5487
Max Act: 4.7675. Min Act: -0.1700
Data Index: 5289673 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5487. Min Range: -5.5487
Max Act: 4.7675. Min Act: -0.1700
Data Index: 22613 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5487. Min Range: -5.5487
Max Act: 4.7675. Min Act: -0.1700
Data Index: 306785 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5487. Min Range: -5.5487
Max Act: 4.7362. Min Act: -0.1700
Data Index: 4570491 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5487. Min Range: -5.5487
Max Act: 4.7050. Min Act: -0.1700
Data Index: 4626393 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5487. Min Range: -5.5487
Max Act: 4.7050. Min Act: -0.1700
Data Index: 7416215 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5487. Min Range: -5.5487
Max Act: 4.6737. Min Act: -0.1700
Data Index: 3695517 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5487. Min Range: -5.5487
Max Act: 4.6737. Min Act: -0.1700
Data Index: 3890735 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5487. Min Range: -5.5487
Max Act: 4.6424. Min Act: -0.1700
Data Index: 2392516 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19