Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2101 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9525. Min Range: -3.9525
Max Act: 3.9525. Min Act: -0.1700
Data Index: 5118567 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9525. Min Range: -3.9525
Max Act: 3.7961. Min Act: -0.1700
Data Index: 3523933 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9525. Min Range: -3.9525
Max Act: 3.7648. Min Act: -0.1700
Data Index: 326689 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9525. Min Range: -3.9525
Max Act: 3.7648. Min Act: -0.1700
Data Index: 4244597 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9525. Min Range: -3.9525
Max Act: 3.7648. Min Act: -0.1700
Data Index: 1947945 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9525. Min Range: -3.9525
Max Act: 3.7648. Min Act: -0.1700
Data Index: 315698 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9525. Min Range: -3.9525
Max Act: 3.7336. Min Act: -0.1700
Data Index: 2125186 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9525. Min Range: -3.9525
Max Act: 3.7336. Min Act: -0.1700
Data Index: 8635477 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9525. Min Range: -3.9525
Max Act: 3.7336. Min Act: -0.1700
Data Index: 1743658 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9525. Min Range: -3.9525
Max Act: 3.7336. Min Act: -0.1700
Data Index: 2792780 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9525. Min Range: -3.9525
Max Act: 3.7336. Min Act: -0.1700
Data Index: 1568295 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9525. Min Range: -3.9525
Max Act: 3.7336. Min Act: -0.1700
Data Index: 3384866 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9525. Min Range: -3.9525
Max Act: 3.7336. Min Act: -0.1700
Data Index: 7538677 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9525. Min Range: -3.9525
Max Act: 3.7336. Min Act: -0.1700
Data Index: 1958334 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9525. Min Range: -3.9525
Max Act: 3.7336. Min Act: -0.1700
Data Index: 2450620 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9525. Min Range: -3.9525
Max Act: 3.7336. Min Act: -0.1700
Data Index: 2996364 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9525. Min Range: -3.9525
Max Act: 3.7023. Min Act: -0.1700
Data Index: 1271446 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9525. Min Range: -3.9525
Max Act: 3.7336. Min Act: -0.1700
Data Index: 2401671 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9525. Min Range: -3.9525
Max Act: 3.7336. Min Act: -0.1700
Data Index: 2326215 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9525. Min Range: -3.9525
Max Act: 3.7336. Min Act: -0.1700
Data Index: 3523943 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19