Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 606 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.9929. Min Act: -0.1700
Data Index: 84124 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.9929. Min Act: -0.1700
Data Index: 3266947 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.9616. Min Act: -0.1700
Data Index: 7047693 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.9616. Min Act: -0.1700
Data Index: 4684107 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.9304. Min Act: -0.1700
Data Index: 3755089 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.8679. Min Act: -0.1700
Data Index: 6153145 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.8679. Min Act: -0.1700
Data Index: 3695113 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.8679. Min Act: -0.1700
Data Index: 4791747 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.8366. Min Act: -0.1700
Data Index: 2851 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.8366. Min Act: -0.1700
Data Index: 7622973 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.8054. Min Act: -0.1700
Data Index: 365729 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.8054. Min Act: -0.1700
Data Index: 8277456 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.7741. Min Act: -0.1700
Data Index: 5575694 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.7429. Min Act: -0.1700
Data Index: 7982217 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.7429. Min Act: -0.1700
Data Index: 8334285 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.7741. Min Act: -0.1700
Data Index: 7385403 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.7116. Min Act: -0.1700
Data Index: 8479906 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.7116. Min Act: -0.1700
Data Index: 4091618 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.7116. Min Act: -0.1700
Data Index: 1754649 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.6491. Min Act: -0.1700
Data Index: 6272567 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19