Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5357 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2453. Min Range: -5.2453
Max Act: 5.2453. Min Act: -0.1700
Data Index: 4295711 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2453. Min Range: -5.2453
Max Act: 5.2453. Min Act: -0.1700
Data Index: 6664384 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2453. Min Range: -5.2453
Max Act: 5.2140. Min Act: -0.1700
Data Index: 6575314 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2453. Min Range: -5.2453
Max Act: 5.2140. Min Act: -0.1700
Data Index: 3364184 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2453. Min Range: -5.2453
Max Act: 5.2140. Min Act: -0.1700
Data Index: 860800 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2453. Min Range: -5.2453
Max Act: 5.1828. Min Act: -0.1700
Data Index: 8123597 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2453. Min Range: -5.2453
Max Act: 5.1828. Min Act: -0.1700
Data Index: 1020147 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2453. Min Range: -5.2453
Max Act: 5.1828. Min Act: -0.1700
Data Index: 3896315 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2453. Min Range: -5.2453
Max Act: 5.1828. Min Act: -0.1700
Data Index: 1020145 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2453. Min Range: -5.2453
Max Act: 5.1828. Min Act: -0.1700
Data Index: 2021529 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2453. Min Range: -5.2453
Max Act: 5.1828. Min Act: -0.1700
Data Index: 7178639 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2453. Min Range: -5.2453
Max Act: 5.1828. Min Act: -0.1700
Data Index: 242627 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2453. Min Range: -5.2453
Max Act: 5.1828. Min Act: -0.1700
Data Index: 7071218 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2453. Min Range: -5.2453
Max Act: 5.1515. Min Act: -0.1700
Data Index: 3220173 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2453. Min Range: -5.2453
Max Act: 5.1828. Min Act: -0.1700
Data Index: 4982199 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2453. Min Range: -5.2453
Max Act: 5.1515. Min Act: -0.1700
Data Index: 4640709 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2453. Min Range: -5.2453
Max Act: 5.1515. Min Act: -0.1700
Data Index: 3488604 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2453. Min Range: -5.2453
Max Act: 5.1515. Min Act: -0.1700
Data Index: 4055913 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2453. Min Range: -5.2453
Max Act: 5.1515. Min Act: -0.1700
Data Index: 5163704 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2453. Min Range: -5.2453
Max Act: 5.1515. Min Act: -0.1700
Data Index: 6545620 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19