Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2826 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6462. Min Range: -7.6462
Max Act: 7.6150. Min Act: -0.1700
Data Index: 3786966 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6462. Min Range: -7.6462
Max Act: 7.6462. Min Act: -0.1700
Data Index: 1429197 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6462. Min Range: -7.6462
Max Act: 7.3962. Min Act: -0.1700
Data Index: 3244307 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6462. Min Range: -7.6462
Max Act: 7.3025. Min Act: -0.1700
Data Index: 593869 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6462. Min Range: -7.6462
Max Act: 7.3025. Min Act: -0.1700
Data Index: 3280804 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6462. Min Range: -7.6462
Max Act: 7.2400. Min Act: -0.1700
Data Index: 5185372 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6462. Min Range: -7.6462
Max Act: 7.1462. Min Act: -0.1700
Data Index: 7427661 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6462. Min Range: -7.6462
Max Act: 7.1150. Min Act: -0.1700
Data Index: 103153 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6462. Min Range: -7.6462
Max Act: 7.0837. Min Act: -0.1700
Data Index: 2778183 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6462. Min Range: -7.6462
Max Act: 7.0837. Min Act: -0.1700
Data Index: 4416990 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6462. Min Range: -7.6462
Max Act: 7.0212. Min Act: -0.1700
Data Index: 440211 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6462. Min Range: -7.6462
Max Act: 7.0212. Min Act: -0.1700
Data Index: 1113328 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6462. Min Range: -7.6462
Max Act: 7.0212. Min Act: -0.1700
Data Index: 4829233 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6462. Min Range: -7.6462
Max Act: 6.9587. Min Act: -0.1700
Data Index: 4948125 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6462. Min Range: -7.6462
Max Act: 7.0212. Min Act: -0.1700
Data Index: 4977906 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6462. Min Range: -7.6462
Max Act: 6.9900. Min Act: -0.1700
Data Index: 7504788 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6462. Min Range: -7.6462
Max Act: 6.9587. Min Act: -0.1700
Data Index: 2482909 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6462. Min Range: -7.6462
Max Act: 6.9587. Min Act: -0.1700
Data Index: 6747253 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6462. Min Range: -7.6462
Max Act: 6.9275. Min Act: -0.1700
Data Index: 6930420 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6462. Min Range: -7.6462
Max Act: 6.9587. Min Act: -0.1700
Data Index: 6878055 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #19