Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1064 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8957. Min Range: -4.8957
Max Act: 4.8957. Min Act: -0.1700
Data Index: 4801291 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8957. Min Range: -4.8957
Max Act: 4.8019. Min Act: -0.1700
Data Index: 1712100 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8957. Min Range: -4.8957
Max Act: 4.7707. Min Act: -0.1700
Data Index: 8185015 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8957. Min Range: -4.8957
Max Act: 4.7394. Min Act: -0.1700
Data Index: 1148016 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8957. Min Range: -4.8957
Max Act: 4.7082. Min Act: -0.1700
Data Index: 4069555 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8957. Min Range: -4.8957
Max Act: 4.6457. Min Act: -0.1700
Data Index: 6045195 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8957. Min Range: -4.8957
Max Act: 4.6457. Min Act: -0.1700
Data Index: 78360 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8957. Min Range: -4.8957
Max Act: 4.6144. Min Act: -0.1700
Data Index: 7587453 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8957. Min Range: -4.8957
Max Act: 4.5832. Min Act: -0.1700
Data Index: 6964230 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8957. Min Range: -4.8957
Max Act: 4.5519. Min Act: -0.1700
Data Index: 7987105 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8957. Min Range: -4.8957
Max Act: 4.5207. Min Act: -0.1700
Data Index: 2802626 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8957. Min Range: -4.8957
Max Act: 4.5207. Min Act: -0.1700
Data Index: 3998235 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8957. Min Range: -4.8957
Max Act: 4.5832. Min Act: -0.1700
Data Index: 1312166 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8957. Min Range: -4.8957
Max Act: 4.5832. Min Act: -0.1700
Data Index: 7290227 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8957. Min Range: -4.8957
Max Act: 4.5207. Min Act: -0.1700
Data Index: 7426884 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8957. Min Range: -4.8957
Max Act: 4.5207. Min Act: -0.1700
Data Index: 2413686 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8957. Min Range: -4.8957
Max Act: 4.5207. Min Act: -0.1700
Data Index: 2404282 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8957. Min Range: -4.8957
Max Act: 4.4894. Min Act: -0.1700
Data Index: 3628321 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8957. Min Range: -4.8957
Max Act: 4.4582. Min Act: -0.1700
Data Index: 632709 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8957. Min Range: -4.8957
Max Act: 4.4894. Min Act: -0.1700
Data Index: 3332026 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19