Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2400 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6278. Min Range: -7.6278
Max Act: 7.6278. Min Act: -0.1700
Data Index: 3967803 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6278. Min Range: -7.6278
Max Act: 7.5653. Min Act: -0.1700
Data Index: 8411416 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6278. Min Range: -7.6278
Max Act: 7.6278. Min Act: -0.1700
Data Index: 7062555 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6278. Min Range: -7.6278
Max Act: 7.4403. Min Act: -0.1700
Data Index: 2952805 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6278. Min Range: -7.6278
Max Act: 7.4403. Min Act: -0.1700
Data Index: 7082590 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6278. Min Range: -7.6278
Max Act: 7.4403. Min Act: -0.1700
Data Index: 6846812 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6278. Min Range: -7.6278
Max Act: 7.4403. Min Act: -0.1700
Data Index: 2668645 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6278. Min Range: -7.6278
Max Act: 7.3778. Min Act: -0.1700
Data Index: 4458687 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6278. Min Range: -7.6278
Max Act: 7.3778. Min Act: -0.1700
Data Index: 7071568 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6278. Min Range: -7.6278
Max Act: 7.3153. Min Act: -0.1700
Data Index: 2172897 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6278. Min Range: -7.6278
Max Act: 7.2528. Min Act: -0.1700
Data Index: 6207254 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6278. Min Range: -7.6278
Max Act: 7.2528. Min Act: -0.1700
Data Index: 5094458 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6278. Min Range: -7.6278
Max Act: 7.1903. Min Act: -0.1700
Data Index: 643880 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6278. Min Range: -7.6278
Max Act: 7.1903. Min Act: -0.1700
Data Index: 8405733 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6278. Min Range: -7.6278
Max Act: 7.1278. Min Act: -0.1700
Data Index: 549029 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6278. Min Range: -7.6278
Max Act: 7.1278. Min Act: -0.1700
Data Index: 155599 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6278. Min Range: -7.6278
Max Act: 7.1278. Min Act: -0.1700
Data Index: 7674808 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6278. Min Range: -7.6278
Max Act: 7.0966. Min Act: -0.1700
Data Index: 894530 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6278. Min Range: -7.6278
Max Act: 7.1591. Min Act: -0.1700
Data Index: 4354840 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6278. Min Range: -7.6278
Max Act: 7.1591. Min Act: -0.1700
Data Index: 3566220 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19