Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1971 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0454. Min Range: -3.0454
Max Act: 3.0454. Min Act: -0.1700
Data Index: 5898093 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0454. Min Range: -3.0454
Max Act: 2.9980. Min Act: -0.1700
Data Index: 594027 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0454. Min Range: -3.0454
Max Act: 2.9980. Min Act: -0.1700
Data Index: 4486424 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0454. Min Range: -3.0454
Max Act: 2.9822. Min Act: -0.1700
Data Index: 3895356 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0454. Min Range: -3.0454
Max Act: 2.9506. Min Act: -0.1700
Data Index: 356570 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0454. Min Range: -3.0454
Max Act: 2.9347. Min Act: -0.1700
Data Index: 1139804 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0454. Min Range: -3.0454
Max Act: 2.9506. Min Act: -0.1700
Data Index: 4279193 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0454. Min Range: -3.0454
Max Act: 2.9347. Min Act: -0.1700
Data Index: 8322827 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0454. Min Range: -3.0454
Max Act: 2.9347. Min Act: -0.1700
Data Index: 4434676 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0454. Min Range: -3.0454
Max Act: 2.9506. Min Act: -0.1700
Data Index: 8204044 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0454. Min Range: -3.0454
Max Act: 2.9347. Min Act: -0.1700
Data Index: 2060553 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0454. Min Range: -3.0454
Max Act: 2.9347. Min Act: -0.1700
Data Index: 1360771 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0454. Min Range: -3.0454
Max Act: 2.9189. Min Act: -0.1700
Data Index: 356914 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0454. Min Range: -3.0454
Max Act: 2.9189. Min Act: -0.1700
Data Index: 2406818 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0454. Min Range: -3.0454
Max Act: 2.9347. Min Act: -0.1700
Data Index: 1507066 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0454. Min Range: -3.0454
Max Act: 2.9189. Min Act: -0.1700
Data Index: 6784554 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0454. Min Range: -3.0454
Max Act: 2.9347. Min Act: -0.1700
Data Index: 6761759 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0454. Min Range: -3.0454
Max Act: 2.9347. Min Act: -0.1700
Data Index: 939305 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0454. Min Range: -3.0454
Max Act: 2.9189. Min Act: -0.1700
Data Index: 6054706 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0454. Min Range: -3.0454
Max Act: 2.9347. Min Act: -0.1700
Data Index: 4702325 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19