Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1120 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2905. Min Range: -7.2905
Max Act: 7.2905. Min Act: -0.1700
Data Index: 8556546 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2905. Min Range: -7.2905
Max Act: 7.0093. Min Act: -0.1700
Data Index: 4783236 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2905. Min Range: -7.2905
Max Act: 6.8843. Min Act: -0.1700
Data Index: 1823095 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2905. Min Range: -7.2905
Max Act: 6.7905. Min Act: -0.1700
Data Index: 3711210 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2905. Min Range: -7.2905
Max Act: 6.8218. Min Act: -0.1700
Data Index: 3788686 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2905. Min Range: -7.2905
Max Act: 6.8218. Min Act: -0.1700
Data Index: 2355894 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2905. Min Range: -7.2905
Max Act: 6.8218. Min Act: -0.1700
Data Index: 6555029 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2905. Min Range: -7.2905
Max Act: 6.8218. Min Act: -0.1700
Data Index: 4124341 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2905. Min Range: -7.2905
Max Act: 6.7905. Min Act: -0.1700
Data Index: 5609728 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2905. Min Range: -7.2905
Max Act: 6.8218. Min Act: -0.1700
Data Index: 3944629 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2905. Min Range: -7.2905
Max Act: 6.7905. Min Act: -0.1700
Data Index: 2299495 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2905. Min Range: -7.2905
Max Act: 6.7905. Min Act: -0.1700
Data Index: 530862 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2905. Min Range: -7.2905
Max Act: 6.7593. Min Act: -0.1700
Data Index: 243674 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2905. Min Range: -7.2905
Max Act: 6.7280. Min Act: -0.1700
Data Index: 7279279 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2905. Min Range: -7.2905
Max Act: 6.7593. Min Act: -0.1700
Data Index: 2850922 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2905. Min Range: -7.2905
Max Act: 6.6968. Min Act: -0.1700
Data Index: 63375 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2905. Min Range: -7.2905
Max Act: 6.7280. Min Act: -0.1700
Data Index: 6489422 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2905. Min Range: -7.2905
Max Act: 6.7280. Min Act: -0.1700
Data Index: 2029865 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2905. Min Range: -7.2905
Max Act: 6.6968. Min Act: -0.1700
Data Index: 4085269 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2905. Min Range: -7.2905
Max Act: 6.6655. Min Act: -0.1700
Data Index: 8148816 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19