Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4026 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2033. Min Range: -4.2033
Max Act: 4.2033. Min Act: -0.1700
Data Index: 2787494 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2033. Min Range: -4.2033
Max Act: 4.1095. Min Act: -0.1700
Data Index: 3972709 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2033. Min Range: -4.2033
Max Act: 4.0783. Min Act: -0.1700
Data Index: 3885792 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2033. Min Range: -4.2033
Max Act: 4.0470. Min Act: -0.1700
Data Index: 122254 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2033. Min Range: -4.2033
Max Act: 4.0158. Min Act: -0.1700
Data Index: 976894 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2033. Min Range: -4.2033
Max Act: 4.0470. Min Act: -0.1700
Data Index: 7118951 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2033. Min Range: -4.2033
Max Act: 4.0470. Min Act: -0.1700
Data Index: 3833138 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2033. Min Range: -4.2033
Max Act: 4.0158. Min Act: -0.1700
Data Index: 1888372 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2033. Min Range: -4.2033
Max Act: 3.9845. Min Act: -0.1700
Data Index: 522413 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2033. Min Range: -4.2033
Max Act: 3.9845. Min Act: -0.1700
Data Index: 6982373 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2033. Min Range: -4.2033
Max Act: 3.9845. Min Act: -0.1700
Data Index: 8537889 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2033. Min Range: -4.2033
Max Act: 3.9532. Min Act: -0.1700
Data Index: 7088523 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2033. Min Range: -4.2033
Max Act: 3.9532. Min Act: -0.1700
Data Index: 4623133 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2033. Min Range: -4.2033
Max Act: 3.9532. Min Act: -0.1700
Data Index: 2398608 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2033. Min Range: -4.2033
Max Act: 3.9220. Min Act: -0.1700
Data Index: 2475602 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2033. Min Range: -4.2033
Max Act: 3.9220. Min Act: -0.1700
Data Index: 8588174 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2033. Min Range: -4.2033
Max Act: 3.9532. Min Act: -0.1700
Data Index: 3390224 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2033. Min Range: -4.2033
Max Act: 3.9220. Min Act: -0.1700
Data Index: 8122822 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2033. Min Range: -4.2033
Max Act: 3.8907. Min Act: -0.1700
Data Index: 4729559 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2033. Min Range: -4.2033
Max Act: 3.8594. Min Act: -0.1700
Data Index: 3485438 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19