Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2919 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9548. Min Range: -8.9548
Max Act: 8.9548. Min Act: -0.1700
Data Index: 440237 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9548. Min Range: -8.9548
Max Act: 8.4548. Min Act: -0.1700
Data Index: 4058769 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9548. Min Range: -8.9548
Max Act: 8.3298. Min Act: -0.1700
Data Index: 2115810 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9548. Min Range: -8.9548
Max Act: 8.2673. Min Act: -0.1700
Data Index: 8643955 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9548. Min Range: -8.9548
Max Act: 8.2673. Min Act: -0.1700
Data Index: 3118043 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9548. Min Range: -8.9548
Max Act: 8.2048. Min Act: -0.1700
Data Index: 8069559 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9548. Min Range: -8.9548
Max Act: 8.2048. Min Act: -0.1700
Data Index: 2713149 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9548. Min Range: -8.9548
Max Act: 8.1423. Min Act: -0.1700
Data Index: 5065327 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9548. Min Range: -8.9548
Max Act: 8.0798. Min Act: -0.1700
Data Index: 4666502 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9548. Min Range: -8.9548
Max Act: 8.0798. Min Act: -0.1700
Data Index: 1220606 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9548. Min Range: -8.9548
Max Act: 8.1423. Min Act: -0.1700
Data Index: 7360195 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9548. Min Range: -8.9548
Max Act: 8.0173. Min Act: -0.1700
Data Index: 8014992 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9548. Min Range: -8.9548
Max Act: 8.0173. Min Act: -0.1700
Data Index: 6524580 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9548. Min Range: -8.9548
Max Act: 7.9548. Min Act: -0.1700
Data Index: 6175412 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9548. Min Range: -8.9548
Max Act: 7.9548. Min Act: -0.1700
Data Index: 6164357 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9548. Min Range: -8.9548
Max Act: 7.9548. Min Act: -0.1700
Data Index: 5510226 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9548. Min Range: -8.9548
Max Act: 7.9548. Min Act: -0.1700
Data Index: 8520669 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9548. Min Range: -8.9548
Max Act: 7.9548. Min Act: -0.1700
Data Index: 4112471 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9548. Min Range: -8.9548
Max Act: 7.8923. Min Act: -0.1700
Data Index: 7195994 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9548. Min Range: -8.9548
Max Act: 7.8923. Min Act: -0.1700
Data Index: 743691 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19