Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 873 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7225. Min Range: -5.7225
Max Act: 5.7225. Min Act: -0.1700
Data Index: 832225 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7225. Min Range: -5.7225
Max Act: 5.6600. Min Act: -0.1700
Data Index: 251533 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7225. Min Range: -5.7225
Max Act: 5.6913. Min Act: -0.1700
Data Index: 333395 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7225. Min Range: -5.7225
Max Act: 5.6600. Min Act: -0.1700
Data Index: 5420965 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7225. Min Range: -5.7225
Max Act: 5.5663. Min Act: -0.1700
Data Index: 4585024 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7225. Min Range: -5.7225
Max Act: 5.5975. Min Act: -0.1700
Data Index: 4585028 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7225. Min Range: -5.7225
Max Act: 5.5663. Min Act: -0.1700
Data Index: 3478757 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7225. Min Range: -5.7225
Max Act: 5.5663. Min Act: -0.1700
Data Index: 4012603 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7225. Min Range: -5.7225
Max Act: 5.5663. Min Act: -0.1700
Data Index: 4148886 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7225. Min Range: -5.7225
Max Act: 5.5350. Min Act: -0.1700
Data Index: 6843013 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7225. Min Range: -5.7225
Max Act: 5.5038. Min Act: -0.1700
Data Index: 608092 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7225. Min Range: -5.7225
Max Act: 5.5038. Min Act: -0.1700
Data Index: 6404286 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7225. Min Range: -5.7225
Max Act: 5.5038. Min Act: -0.1700
Data Index: 6109679 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7225. Min Range: -5.7225
Max Act: 5.4725. Min Act: -0.1700
Data Index: 317184 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7225. Min Range: -5.7225
Max Act: 5.4413. Min Act: -0.1700
Data Index: 921171 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7225. Min Range: -5.7225
Max Act: 5.4413. Min Act: -0.1700
Data Index: 1054806 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7225. Min Range: -5.7225
Max Act: 5.4100. Min Act: -0.1700
Data Index: 1390321 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7225. Min Range: -5.7225
Max Act: 5.4100. Min Act: -0.1700
Data Index: 2012431 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7225. Min Range: -5.7225
Max Act: 5.4100. Min Act: -0.1700
Data Index: 3168968 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7225. Min Range: -5.7225
Max Act: 5.3475. Min Act: -0.1700
Data Index: 4369025 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19