Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3363 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5990. Min Range: -2.5990
Max Act: 2.5990. Min Act: -0.1700
Data Index: 1436100 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5990. Min Range: -2.5990
Max Act: 2.5668. Min Act: -0.1700
Data Index: 8255808 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5990. Min Range: -2.5990
Max Act: 2.5183. Min Act: -0.1700
Data Index: 1059921 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5990. Min Range: -2.5990
Max Act: 2.5021. Min Act: -0.1700
Data Index: 2423243 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5990. Min Range: -2.5990
Max Act: 2.4697. Min Act: -0.1700
Data Index: 4189632 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5990. Min Range: -2.5990
Max Act: 2.4697. Min Act: -0.1700
Data Index: 645848 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5990. Min Range: -2.5990
Max Act: 2.4859. Min Act: -0.1700
Data Index: 8702263 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5990. Min Range: -2.5990
Max Act: 2.4859. Min Act: -0.1700
Data Index: 7594455 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5990. Min Range: -2.5990
Max Act: 2.4697. Min Act: -0.1700
Data Index: 7110358 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5990. Min Range: -2.5990
Max Act: 2.4697. Min Act: -0.1700
Data Index: 512248 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5990. Min Range: -2.5990
Max Act: 2.4859. Min Act: -0.1700
Data Index: 6607237 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5990. Min Range: -2.5990
Max Act: 2.4697. Min Act: -0.1700
Data Index: 3699641 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5990. Min Range: -2.5990
Max Act: 2.4372. Min Act: -0.1700
Data Index: 2239375 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5990. Min Range: -2.5990
Max Act: 2.4535. Min Act: -0.1700
Data Index: 6581366 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5990. Min Range: -2.5990
Max Act: 2.4535. Min Act: -0.1700
Data Index: 3970962 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5990. Min Range: -2.5990
Max Act: 2.4535. Min Act: -0.1700
Data Index: 1915290 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5990. Min Range: -2.5990
Max Act: 2.4372. Min Act: -0.1700
Data Index: 1378871 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5990. Min Range: -2.5990
Max Act: 2.4372. Min Act: -0.1700
Data Index: 1574234 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5990. Min Range: -2.5990
Max Act: 2.4535. Min Act: -0.1700
Data Index: 5679363 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5990. Min Range: -2.5990
Max Act: 2.4535. Min Act: -0.1700
Data Index: 1691328 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19