Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2044 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.9337. Min Act: -0.1700
Data Index: 5649150 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.9025. Min Act: -0.1700
Data Index: 7328713 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.9025. Min Act: -0.1700
Data Index: 6829254 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.8712. Min Act: -0.1700
Data Index: 235964 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.8712. Min Act: -0.1700
Data Index: 2028460 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.8712. Min Act: -0.1700
Data Index: 2170201 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.8087. Min Act: -0.1700
Data Index: 2228602 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.8400. Min Act: -0.1700
Data Index: 3418933 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.8087. Min Act: -0.1700
Data Index: 5340788 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.7462. Min Act: -0.1700
Data Index: 3850253 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.7150. Min Act: -0.1700
Data Index: 3732931 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.7462. Min Act: -0.1700
Data Index: 2588197 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.7150. Min Act: -0.1700
Data Index: 4627386 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.7150. Min Act: -0.1700
Data Index: 6491170 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.6837. Min Act: -0.1700
Data Index: 6708868 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.6837. Min Act: -0.1700
Data Index: 5783643 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.6837. Min Act: -0.1700
Data Index: 4140104 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.6837. Min Act: -0.1700
Data Index: 4056677 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.6837. Min Act: -0.1700
Data Index: 5970789 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.6837. Min Act: -0.1700
Data Index: 5181601 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #19