Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 98 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0394. Min Range: -6.0394
Max Act: 6.0394. Min Act: -0.1700
Data Index: 1506610 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0394. Min Range: -6.0394
Max Act: 5.8832. Min Act: -0.1700
Data Index: 8267251 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0394. Min Range: -6.0394
Max Act: 5.7894. Min Act: -0.1700
Data Index: 5837762 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0394. Min Range: -6.0394
Max Act: 5.7269. Min Act: -0.1700
Data Index: 273065 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0394. Min Range: -6.0394
Max Act: 5.5082. Min Act: -0.1700
Data Index: 1627014 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0394. Min Range: -6.0394
Max Act: 5.5394. Min Act: -0.1700
Data Index: 8693207 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0394. Min Range: -6.0394
Max Act: 5.4769. Min Act: -0.1700
Data Index: 5763873 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0394. Min Range: -6.0394
Max Act: 5.4769. Min Act: -0.1700
Data Index: 3103523 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0394. Min Range: -6.0394
Max Act: 5.5082. Min Act: -0.1700
Data Index: 6350477 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0394. Min Range: -6.0394
Max Act: 5.4769. Min Act: -0.1700
Data Index: 1411424 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0394. Min Range: -6.0394
Max Act: 5.4457. Min Act: -0.1700
Data Index: 1301790 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0394. Min Range: -6.0394
Max Act: 5.4144. Min Act: -0.1700
Data Index: 6595893 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0394. Min Range: -6.0394
Max Act: 5.4457. Min Act: -0.1700
Data Index: 3416240 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0394. Min Range: -6.0394
Max Act: 5.4144. Min Act: -0.1700
Data Index: 5229700 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0394. Min Range: -6.0394
Max Act: 5.4144. Min Act: -0.1700
Data Index: 6381245 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0394. Min Range: -6.0394
Max Act: 5.4144. Min Act: -0.1700
Data Index: 4232669 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0394. Min Range: -6.0394
Max Act: 5.4144. Min Act: -0.1700
Data Index: 7894314 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0394. Min Range: -6.0394
Max Act: 5.4144. Min Act: -0.1700
Data Index: 4481731 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0394. Min Range: -6.0394
Max Act: 5.4144. Min Act: -0.1700
Data Index: 2532019 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0394. Min Range: -6.0394
Max Act: 5.4457. Min Act: -0.1700
Data Index: 5443353 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19