Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3779 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.6480. Min Act: -0.1700
Data Index: 7307649 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.4917. Min Act: -0.1700
Data Index: 1899632 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.4917. Min Act: -0.1700
Data Index: 5653026 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.3980. Min Act: -0.1700
Data Index: 4514130 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.3667. Min Act: -0.1700
Data Index: 4490243 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.3042. Min Act: -0.1700
Data Index: 1519643 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.3355. Min Act: -0.1700
Data Index: 5414215 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.2730. Min Act: -0.1700
Data Index: 1778962 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.2417. Min Act: -0.1700
Data Index: 7172407 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.2730. Min Act: -0.1700
Data Index: 8302416 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.2417. Min Act: -0.1700
Data Index: 1389961 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.2105. Min Act: -0.1700
Data Index: 427535 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.2105. Min Act: -0.1700
Data Index: 2037268 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.2105. Min Act: -0.1700
Data Index: 5606753 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.2105. Min Act: -0.1700
Data Index: 4895780 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.1792. Min Act: -0.1700
Data Index: 4140895 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.1792. Min Act: -0.1700
Data Index: 5379491 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.1480. Min Act: -0.1700
Data Index: 1389960 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.1167. Min Act: -0.1700
Data Index: 3104169 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.1167. Min Act: -0.1700
Data Index: 5606750 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19