Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4824 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9635. Min Range: -9.9635
Max Act: 9.9635. Min Act: -0.1700
Data Index: 1517259 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9635. Min Range: -9.9635
Max Act: 9.9010. Min Act: -0.1700
Data Index: 5695646 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9635. Min Range: -9.9635
Max Act: 9.2760. Min Act: -0.1700
Data Index: 7642654 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9635. Min Range: -9.9635
Max Act: 9.2135. Min Act: -0.1700
Data Index: 4256567 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9635. Min Range: -9.9635
Max Act: 9.1510. Min Act: -0.1700
Data Index: 2810658 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9635. Min Range: -9.9635
Max Act: 9.1510. Min Act: -0.1700
Data Index: 3677012 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9635. Min Range: -9.9635
Max Act: 9.0885. Min Act: -0.1700
Data Index: 4636654 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9635. Min Range: -9.9635
Max Act: 8.8385. Min Act: -0.1700
Data Index: 5171921 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9635. Min Range: -9.9635
Max Act: 8.6510. Min Act: -0.1700
Data Index: 3929640 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9635. Min Range: -9.9635
Max Act: 8.2447. Min Act: -0.1700
Data Index: 2016807 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9635. Min Range: -9.9635
Max Act: 8.2447. Min Act: -0.1700
Data Index: 977296 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9635. Min Range: -9.9635
Max Act: 8.2135. Min Act: -0.1700
Data Index: 281482 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9635. Min Range: -9.9635
Max Act: 8.1822. Min Act: -0.1700
Data Index: 7101075 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9635. Min Range: -9.9635
Max Act: 8.1197. Min Act: -0.1700
Data Index: 1517261 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9635. Min Range: -9.9635
Max Act: 8.1197. Min Act: -0.1700
Data Index: 4249515 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9635. Min Range: -9.9635
Max Act: 8.0572. Min Act: -0.1700
Data Index: 4671352 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9635. Min Range: -9.9635
Max Act: 8.1197. Min Act: -0.1700
Data Index: 3282576 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9635. Min Range: -9.9635
Max Act: 8.0885. Min Act: -0.1700
Data Index: 1761564 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9635. Min Range: -9.9635
Max Act: 8.0260. Min Act: -0.1700
Data Index: 6629249 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9635. Min Range: -9.9635
Max Act: 8.0260. Min Act: -0.1700
Data Index: 3011448 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19