Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4598 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9523. Min Range: -5.9523
Max Act: 5.9523. Min Act: -0.1700
Data Index: 4802677 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9523. Min Range: -5.9523
Max Act: 5.6398. Min Act: -0.1700
Data Index: 1794807 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9523. Min Range: -5.9523
Max Act: 5.5460. Min Act: -0.1700
Data Index: 382805 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9523. Min Range: -5.9523
Max Act: 5.2960. Min Act: -0.1700
Data Index: 7761615 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9523. Min Range: -5.9523
Max Act: 5.2960. Min Act: -0.1700
Data Index: 6857145 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9523. Min Range: -5.9523
Max Act: 5.2648. Min Act: -0.1700
Data Index: 3801991 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9523. Min Range: -5.9523
Max Act: 5.2960. Min Act: -0.1700
Data Index: 5194506 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9523. Min Range: -5.9523
Max Act: 5.2335. Min Act: -0.1700
Data Index: 5293888 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9523. Min Range: -5.9523
Max Act: 5.2023. Min Act: -0.1700
Data Index: 2601966 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9523. Min Range: -5.9523
Max Act: 5.1710. Min Act: -0.1700
Data Index: 482144 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9523. Min Range: -5.9523
Max Act: 5.1398. Min Act: -0.1700
Data Index: 8136311 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9523. Min Range: -5.9523
Max Act: 5.0773. Min Act: -0.1700
Data Index: 2367 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9523. Min Range: -5.9523
Max Act: 5.0773. Min Act: -0.1700
Data Index: 859750 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9523. Min Range: -5.9523
Max Act: 5.0773. Min Act: -0.1700
Data Index: 7634809 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9523. Min Range: -5.9523
Max Act: 5.0773. Min Act: -0.1700
Data Index: 6816790 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9523. Min Range: -5.9523
Max Act: 5.0460. Min Act: -0.1700
Data Index: 6077140 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9523. Min Range: -5.9523
Max Act: 5.0460. Min Act: -0.1700
Data Index: 382807 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9523. Min Range: -5.9523
Max Act: 5.0460. Min Act: -0.1700
Data Index: 8456037 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9523. Min Range: -5.9523
Max Act: 5.0148. Min Act: -0.1700
Data Index: 1521816 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9523. Min Range: -5.9523
Max Act: 5.0148. Min Act: -0.1700
Data Index: 6297721 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19