Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4952 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2900. Min Range: -6.2900
Max Act: 6.2900. Min Act: -0.1700
Data Index: 7525187 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2900. Min Range: -6.2900
Max Act: 6.0087. Min Act: -0.1700
Data Index: 8795028 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2900. Min Range: -6.2900
Max Act: 5.9775. Min Act: -0.1700
Data Index: 7071519 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2900. Min Range: -6.2900
Max Act: 6.0087. Min Act: -0.1700
Data Index: 1464856 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2900. Min Range: -6.2900
Max Act: 5.9775. Min Act: -0.1700
Data Index: 519990 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2900. Min Range: -6.2900
Max Act: 5.9150. Min Act: -0.1700
Data Index: 4375461 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2900. Min Range: -6.2900
Max Act: 5.9462. Min Act: -0.1700
Data Index: 2271958 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2900. Min Range: -6.2900
Max Act: 5.9150. Min Act: -0.1700
Data Index: 8218707 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2900. Min Range: -6.2900
Max Act: 5.8837. Min Act: -0.1700
Data Index: 4121879 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2900. Min Range: -6.2900
Max Act: 5.8837. Min Act: -0.1700
Data Index: 8708669 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2900. Min Range: -6.2900
Max Act: 5.8837. Min Act: -0.1700
Data Index: 4914038 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2900. Min Range: -6.2900
Max Act: 5.8212. Min Act: -0.1700
Data Index: 4321732 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2900. Min Range: -6.2900
Max Act: 5.8525. Min Act: -0.1700
Data Index: 4592688 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2900. Min Range: -6.2900
Max Act: 5.8525. Min Act: -0.1700
Data Index: 2789735 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2900. Min Range: -6.2900
Max Act: 5.8525. Min Act: -0.1700
Data Index: 6759002 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2900. Min Range: -6.2900
Max Act: 5.8212. Min Act: -0.1700
Data Index: 149432 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2900. Min Range: -6.2900
Max Act: 5.8212. Min Act: -0.1700
Data Index: 6404332 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2900. Min Range: -6.2900
Max Act: 5.8212. Min Act: -0.1700
Data Index: 778052 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2900. Min Range: -6.2900
Max Act: 5.8212. Min Act: -0.1700
Data Index: 1229876 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2900. Min Range: -6.2900
Max Act: 5.8212. Min Act: -0.1700
Data Index: 4898568 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19