Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2045 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6095. Min Range: -4.6095
Max Act: 4.6095. Min Act: -0.1700
Data Index: 5789166 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6095. Min Range: -4.6095
Max Act: 4.2032. Min Act: -0.1700
Data Index: 1759497 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6095. Min Range: -4.6095
Max Act: 4.2032. Min Act: -0.1700
Data Index: 1690200 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6095. Min Range: -4.6095
Max Act: 4.1720. Min Act: -0.1700
Data Index: 2032337 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6095. Min Range: -4.6095
Max Act: 4.1095. Min Act: -0.1700
Data Index: 7858198 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6095. Min Range: -4.6095
Max Act: 4.0157. Min Act: -0.1700
Data Index: 1956925 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6095. Min Range: -4.6095
Max Act: 4.0469. Min Act: -0.1700
Data Index: 215619 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6095. Min Range: -4.6095
Max Act: 4.0469. Min Act: -0.1700
Data Index: 1759498 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6095. Min Range: -4.6095
Max Act: 3.9844. Min Act: -0.1700
Data Index: 4919530 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6095. Min Range: -4.6095
Max Act: 3.9219. Min Act: -0.1700
Data Index: 7482238 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6095. Min Range: -4.6095
Max Act: 3.8906. Min Act: -0.1700
Data Index: 1088880 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6095. Min Range: -4.6095
Max Act: 3.9219. Min Act: -0.1700
Data Index: 7799879 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6095. Min Range: -4.6095
Max Act: 3.8906. Min Act: -0.1700
Data Index: 1615378 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6095. Min Range: -4.6095
Max Act: 3.8906. Min Act: -0.1700
Data Index: 5112549 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6095. Min Range: -4.6095
Max Act: 3.8594. Min Act: -0.1700
Data Index: 1759487 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6095. Min Range: -4.6095
Max Act: 3.8594. Min Act: -0.1700
Data Index: 4233099 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6095. Min Range: -4.6095
Max Act: 3.8281. Min Act: -0.1700
Data Index: 4692705 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6095. Min Range: -4.6095
Max Act: 3.8594. Min Act: -0.1700
Data Index: 2825410 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6095. Min Range: -4.6095
Max Act: 3.8594. Min Act: -0.1700
Data Index: 3681954 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6095. Min Range: -4.6095
Max Act: 3.8594. Min Act: -0.1700
Data Index: 1617039 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19