Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 546 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1448. Min Range: -2.1448
Max Act: 2.1448. Min Act: -0.1700
Data Index: 2890663 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1448. Min Range: -2.1448
Max Act: 2.1114. Min Act: -0.1700
Data Index: 2545812 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1448. Min Range: -2.1448
Max Act: 2.0947. Min Act: -0.1700
Data Index: 2453010 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1448. Min Range: -2.1448
Max Act: 2.0947. Min Act: -0.1700
Data Index: 7533666 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1448. Min Range: -2.1448
Max Act: 2.0611. Min Act: -0.1700
Data Index: 5457513 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1448. Min Range: -2.1448
Max Act: 2.0611. Min Act: -0.1700
Data Index: 7952350 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1448. Min Range: -2.1448
Max Act: 2.0443. Min Act: -0.1700
Data Index: 5316470 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1448. Min Range: -2.1448
Max Act: 2.0779. Min Act: -0.1700
Data Index: 6919139 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1448. Min Range: -2.1448
Max Act: 2.0443. Min Act: -0.1700
Data Index: 6495251 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1448. Min Range: -2.1448
Max Act: 2.0275. Min Act: -0.1700
Data Index: 1792984 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1448. Min Range: -2.1448
Max Act: 2.0443. Min Act: -0.1700
Data Index: 6617755 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1448. Min Range: -2.1448
Max Act: 2.0275. Min Act: -0.1700
Data Index: 1272620 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1448. Min Range: -2.1448
Max Act: 1.9937. Min Act: -0.1700
Data Index: 6121761 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1448. Min Range: -2.1448
Max Act: 2.0106. Min Act: -0.1700
Data Index: 8599057 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1448. Min Range: -2.1448
Max Act: 2.0275. Min Act: -0.1700
Data Index: 1307510 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1448. Min Range: -2.1448
Max Act: 1.9768. Min Act: -0.1700
Data Index: 8755992 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1448. Min Range: -2.1448
Max Act: 1.9937. Min Act: -0.1700
Data Index: 1502472 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1448. Min Range: -2.1448
Max Act: 1.9768. Min Act: -0.1700
Data Index: 7356698 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1448. Min Range: -2.1448
Max Act: 1.9937. Min Act: -0.1700
Data Index: 4401340 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1448. Min Range: -2.1448
Max Act: 2.0106. Min Act: -0.1699
Data Index: 5625678 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19