Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2823 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4446. Min Range: -7.4446
Max Act: 7.4133. Min Act: -0.1700
Data Index: 3141764 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4446. Min Range: -7.4446
Max Act: 7.4446. Min Act: -0.1700
Data Index: 6165539 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4446. Min Range: -7.4446
Max Act: 7.3508. Min Act: -0.1700
Data Index: 6441753 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4446. Min Range: -7.4446
Max Act: 7.2258. Min Act: -0.1700
Data Index: 2399646 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4446. Min Range: -7.4446
Max Act: 7.1633. Min Act: -0.1700
Data Index: 803236 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4446. Min Range: -7.4446
Max Act: 7.1633. Min Act: -0.1700
Data Index: 6254053 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4446. Min Range: -7.4446
Max Act: 7.1633. Min Act: -0.1700
Data Index: 2957201 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4446. Min Range: -7.4446
Max Act: 7.1321. Min Act: -0.1700
Data Index: 6237525 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4446. Min Range: -7.4446
Max Act: 7.0071. Min Act: -0.1700
Data Index: 2213009 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4446. Min Range: -7.4446
Max Act: 7.0071. Min Act: -0.1700
Data Index: 5344186 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4446. Min Range: -7.4446
Max Act: 6.9758. Min Act: -0.1700
Data Index: 1285491 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4446. Min Range: -7.4446
Max Act: 6.8821. Min Act: -0.1700
Data Index: 6169321 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4446. Min Range: -7.4446
Max Act: 6.8821. Min Act: -0.1700
Data Index: 178673 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4446. Min Range: -7.4446
Max Act: 6.8821. Min Act: -0.1700
Data Index: 7863264 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4446. Min Range: -7.4446
Max Act: 6.8821. Min Act: -0.1700
Data Index: 4606071 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4446. Min Range: -7.4446
Max Act: 6.8508. Min Act: -0.1700
Data Index: 7301024 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4446. Min Range: -7.4446
Max Act: 6.8821. Min Act: -0.1700
Data Index: 1742579 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4446. Min Range: -7.4446
Max Act: 6.8196. Min Act: -0.1700
Data Index: 965113 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4446. Min Range: -7.4446
Max Act: 6.8196. Min Act: -0.1700
Data Index: 2391534 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4446. Min Range: -7.4446
Max Act: 6.8196. Min Act: -0.1700
Data Index: 6718188 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19