Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5890 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6315. Min Range: -6.6315
Max Act: 6.6315. Min Act: -0.1700
Data Index: 7993974 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6315. Min Range: -6.6315
Max Act: 6.5690. Min Act: -0.1700
Data Index: 7781215 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6315. Min Range: -6.6315
Max Act: 6.3503. Min Act: -0.1700
Data Index: 6587076 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6315. Min Range: -6.6315
Max Act: 6.3503. Min Act: -0.1700
Data Index: 3752077 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6315. Min Range: -6.6315
Max Act: 6.2565. Min Act: -0.1700
Data Index: 2317945 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6315. Min Range: -6.6315
Max Act: 6.1940. Min Act: -0.1700
Data Index: 7178423 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6315. Min Range: -6.6315
Max Act: 6.1003. Min Act: -0.1700
Data Index: 4932170 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6315. Min Range: -6.6315
Max Act: 6.1003. Min Act: -0.1700
Data Index: 7585884 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6315. Min Range: -6.6315
Max Act: 6.1315. Min Act: -0.1700
Data Index: 518109 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6315. Min Range: -6.6315
Max Act: 5.9753. Min Act: -0.1700
Data Index: 4616055 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6315. Min Range: -6.6315
Max Act: 5.9753. Min Act: -0.1700
Data Index: 533996 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6315. Min Range: -6.6315
Max Act: 5.9753. Min Act: -0.1700
Data Index: 4589884 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6315. Min Range: -6.6315
Max Act: 5.9440. Min Act: -0.1700
Data Index: 4495873 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6315. Min Range: -6.6315
Max Act: 5.9128. Min Act: -0.1700
Data Index: 8201309 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6315. Min Range: -6.6315
Max Act: 5.9128. Min Act: -0.1700
Data Index: 4184349 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6315. Min Range: -6.6315
Max Act: 5.9440. Min Act: -0.1700
Data Index: 157543 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6315. Min Range: -6.6315
Max Act: 5.9128. Min Act: -0.1700
Data Index: 3258357 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6315. Min Range: -6.6315
Max Act: 5.9128. Min Act: -0.1700
Data Index: 6637570 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6315. Min Range: -6.6315
Max Act: 5.9128. Min Act: -0.1700
Data Index: 6936745 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6315. Min Range: -6.6315
Max Act: 5.8815. Min Act: -0.1700
Data Index: 3971521 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19