Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4987 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6403. Min Range: -4.6403
Max Act: 4.6403. Min Act: -0.1700
Data Index: 5931829 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6403. Min Range: -4.6403
Max Act: 4.6403. Min Act: -0.1700
Data Index: 3880149 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6403. Min Range: -4.6403
Max Act: 4.6091. Min Act: -0.1700
Data Index: 6721416 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6403. Min Range: -4.6403
Max Act: 4.5778. Min Act: -0.1700
Data Index: 5244762 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6403. Min Range: -4.6403
Max Act: 4.5778. Min Act: -0.1700
Data Index: 1885960 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6403. Min Range: -4.6403
Max Act: 4.5778. Min Act: -0.1700
Data Index: 8532259 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6403. Min Range: -4.6403
Max Act: 4.5778. Min Act: -0.1700
Data Index: 533448 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6403. Min Range: -4.6403
Max Act: 4.5466. Min Act: -0.1700
Data Index: 7542447 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6403. Min Range: -4.6403
Max Act: 4.5466. Min Act: -0.1700
Data Index: 8215953 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6403. Min Range: -4.6403
Max Act: 4.5466. Min Act: -0.1700
Data Index: 2370946 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6403. Min Range: -4.6403
Max Act: 4.5466. Min Act: -0.1700
Data Index: 4056500 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6403. Min Range: -4.6403
Max Act: 4.5153. Min Act: -0.1700
Data Index: 6531281 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6403. Min Range: -4.6403
Max Act: 4.5466. Min Act: -0.1700
Data Index: 1982285 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6403. Min Range: -4.6403
Max Act: 4.5153. Min Act: -0.1700
Data Index: 729801 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6403. Min Range: -4.6403
Max Act: 4.5153. Min Act: -0.1700
Data Index: 950382 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6403. Min Range: -4.6403
Max Act: 4.5466. Min Act: -0.1700
Data Index: 4120348 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6403. Min Range: -4.6403
Max Act: 4.5153. Min Act: -0.1700
Data Index: 3293307 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6403. Min Range: -4.6403
Max Act: 4.5153. Min Act: -0.1700
Data Index: 5855359 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6403. Min Range: -4.6403
Max Act: 4.4528. Min Act: -0.1700
Data Index: 2609445 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6403. Min Range: -4.6403
Max Act: 4.4841. Min Act: -0.1700
Data Index: 5736691 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #19