Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3450 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5732. Min Range: -5.5732
Max Act: 5.5732. Min Act: -0.1700
Data Index: 1490911 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5732. Min Range: -5.5732
Max Act: 5.5732. Min Act: -0.1700
Data Index: 7425856 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5732. Min Range: -5.5732
Max Act: 5.5419. Min Act: -0.1700
Data Index: 1974417 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5732. Min Range: -5.5732
Max Act: 5.5732. Min Act: -0.1700
Data Index: 4390254 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5732. Min Range: -5.5732
Max Act: 5.5419. Min Act: -0.1700
Data Index: 616761 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5732. Min Range: -5.5732
Max Act: 5.4794. Min Act: -0.1700
Data Index: 3334572 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5732. Min Range: -5.5732
Max Act: 5.4482. Min Act: -0.1700
Data Index: 3147248 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5732. Min Range: -5.5732
Max Act: 5.4794. Min Act: -0.1700
Data Index: 3922005 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5732. Min Range: -5.5732
Max Act: 5.4794. Min Act: -0.1700
Data Index: 2149565 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5732. Min Range: -5.5732
Max Act: 5.4482. Min Act: -0.1700
Data Index: 1412853 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5732. Min Range: -5.5732
Max Act: 5.4482. Min Act: -0.1700
Data Index: 896600 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5732. Min Range: -5.5732
Max Act: 5.4169. Min Act: -0.1700
Data Index: 3246125 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5732. Min Range: -5.5732
Max Act: 5.3857. Min Act: -0.1700
Data Index: 1218761 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5732. Min Range: -5.5732
Max Act: 5.3544. Min Act: -0.1700
Data Index: 3147242 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5732. Min Range: -5.5732
Max Act: 5.3857. Min Act: -0.1700
Data Index: 7077930 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5732. Min Range: -5.5732
Max Act: 5.3857. Min Act: -0.1700
Data Index: 6352059 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5732. Min Range: -5.5732
Max Act: 5.3544. Min Act: -0.1700
Data Index: 5852217 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5732. Min Range: -5.5732
Max Act: 5.3857. Min Act: -0.1700
Data Index: 4553843 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5732. Min Range: -5.5732
Max Act: 5.3544. Min Act: -0.1700
Data Index: 7652066 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5732. Min Range: -5.5732
Max Act: 5.3857. Min Act: -0.1700
Data Index: 8679450 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19