Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3027 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7499. Min Range: -2.7499
Max Act: 2.7499. Min Act: -0.1700
Data Index: 7112638 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7499. Min Range: -2.7499
Max Act: 2.7499. Min Act: -0.1700
Data Index: 7165112 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7499. Min Range: -2.7499
Max Act: 2.7499. Min Act: -0.1700
Data Index: 7444440 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7499. Min Range: -2.7499
Max Act: 2.7340. Min Act: -0.1700
Data Index: 2437802 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7499. Min Range: -2.7499
Max Act: 2.7340. Min Act: -0.1700
Data Index: 1844335 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7499. Min Range: -2.7499
Max Act: 2.7340. Min Act: -0.1700
Data Index: 4894396 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7499. Min Range: -2.7499
Max Act: 2.7340. Min Act: -0.1700
Data Index: 6739717 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7499. Min Range: -2.7499
Max Act: 2.7020. Min Act: -0.1700
Data Index: 5468241 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7499. Min Range: -2.7499
Max Act: 2.7180. Min Act: -0.1700
Data Index: 2354989 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7499. Min Range: -2.7499
Max Act: 2.7180. Min Act: -0.1700
Data Index: 6633344 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7499. Min Range: -2.7499
Max Act: 2.7180. Min Act: -0.1700
Data Index: 627503 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7499. Min Range: -2.7499
Max Act: 2.7180. Min Act: -0.1700
Data Index: 8220541 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7499. Min Range: -2.7499
Max Act: 2.7180. Min Act: -0.1700
Data Index: 7235264 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7499. Min Range: -2.7499
Max Act: 2.7180. Min Act: -0.1700
Data Index: 6488304 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7499. Min Range: -2.7499
Max Act: 2.7020. Min Act: -0.1700
Data Index: 6645554 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7499. Min Range: -2.7499
Max Act: 2.7180. Min Act: -0.1700
Data Index: 1376262 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7499. Min Range: -2.7499
Max Act: 2.7020. Min Act: -0.1700
Data Index: 373772 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7499. Min Range: -2.7499
Max Act: 2.7180. Min Act: -0.1700
Data Index: 320741 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7499. Min Range: -2.7499
Max Act: 2.7020. Min Act: -0.1700
Data Index: 4906091 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7499. Min Range: -2.7499
Max Act: 2.7020. Min Act: -0.1700
Data Index: 6670752 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19