Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5897 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6201. Min Range: -6.6201
Max Act: 6.6201. Min Act: -0.1700
Data Index: 951879 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6201. Min Range: -6.6201
Max Act: 6.4014. Min Act: -0.1700
Data Index: 7662521 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6201. Min Range: -6.6201
Max Act: 6.3701. Min Act: -0.1700
Data Index: 2921663 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6201. Min Range: -6.6201
Max Act: 6.3389. Min Act: -0.1700
Data Index: 510126 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6201. Min Range: -6.6201
Max Act: 6.3389. Min Act: -0.1700
Data Index: 4952079 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6201. Min Range: -6.6201
Max Act: 6.3389. Min Act: -0.1700
Data Index: 7280380 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6201. Min Range: -6.6201
Max Act: 6.3076. Min Act: -0.1700
Data Index: 6971169 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6201. Min Range: -6.6201
Max Act: 6.3076. Min Act: -0.1700
Data Index: 1648724 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6201. Min Range: -6.6201
Max Act: 6.2764. Min Act: -0.1700
Data Index: 4404413 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6201. Min Range: -6.6201
Max Act: 6.2451. Min Act: -0.1700
Data Index: 1110212 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6201. Min Range: -6.6201
Max Act: 6.2451. Min Act: -0.1700
Data Index: 8537971 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6201. Min Range: -6.6201
Max Act: 6.2139. Min Act: -0.1700
Data Index: 4392656 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6201. Min Range: -6.6201
Max Act: 6.2139. Min Act: -0.1700
Data Index: 3832110 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6201. Min Range: -6.6201
Max Act: 6.2139. Min Act: -0.1700
Data Index: 8231005 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6201. Min Range: -6.6201
Max Act: 6.1826. Min Act: -0.1700
Data Index: 1403338 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6201. Min Range: -6.6201
Max Act: 6.1826. Min Act: -0.1700
Data Index: 8323931 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6201. Min Range: -6.6201
Max Act: 6.1826. Min Act: -0.1700
Data Index: 2561931 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6201. Min Range: -6.6201
Max Act: 6.1826. Min Act: -0.1700
Data Index: 2094756 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6201. Min Range: -6.6201
Max Act: 6.1826. Min Act: -0.1700
Data Index: 7863479 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6201. Min Range: -6.6201
Max Act: 6.1826. Min Act: -0.1700
Data Index: 8698872 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19