Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4595 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1912. Min Range: -7.1912
Max Act: 7.1912. Min Act: -0.1700
Data Index: 2406108 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1912. Min Range: -7.1912
Max Act: 7.1912. Min Act: -0.1700
Data Index: 4370755 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1912. Min Range: -7.1912
Max Act: 6.8787. Min Act: -0.1700
Data Index: 8770146 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1912. Min Range: -7.1912
Max Act: 6.7849. Min Act: -0.1700
Data Index: 8361106 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1912. Min Range: -7.1912
Max Act: 6.5974. Min Act: -0.1700
Data Index: 8286949 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1912. Min Range: -7.1912
Max Act: 6.5974. Min Act: -0.1700
Data Index: 1960953 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1912. Min Range: -7.1912
Max Act: 6.5349. Min Act: -0.1700
Data Index: 147289 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1912. Min Range: -7.1912
Max Act: 6.5662. Min Act: -0.1700
Data Index: 8789969 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1912. Min Range: -7.1912
Max Act: 6.5349. Min Act: -0.1700
Data Index: 2461982 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1912. Min Range: -7.1912
Max Act: 6.5037. Min Act: -0.1700
Data Index: 3115698 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1912. Min Range: -7.1912
Max Act: 6.5037. Min Act: -0.1700
Data Index: 4535912 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1912. Min Range: -7.1912
Max Act: 6.4724. Min Act: -0.1700
Data Index: 3088116 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1912. Min Range: -7.1912
Max Act: 6.4099. Min Act: -0.1700
Data Index: 3905280 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1912. Min Range: -7.1912
Max Act: 6.4412. Min Act: -0.1700
Data Index: 1456045 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1912. Min Range: -7.1912
Max Act: 6.4412. Min Act: -0.1700
Data Index: 1292459 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1912. Min Range: -7.1912
Max Act: 6.4099. Min Act: -0.1700
Data Index: 7975245 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1912. Min Range: -7.1912
Max Act: 6.4099. Min Act: -0.1700
Data Index: 2505627 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1912. Min Range: -7.1912
Max Act: 6.4099. Min Act: -0.1700
Data Index: 5775577 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1912. Min Range: -7.1912
Max Act: 6.3474. Min Act: -0.1700
Data Index: 1881696 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1912. Min Range: -7.1912
Max Act: 6.3474. Min Act: -0.1700
Data Index: 3481278 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19