Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2732 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.9972. Min Act: -0.1700
Data Index: 3476471 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.8097. Min Act: -0.1700
Data Index: 6628787 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.7785. Min Act: -0.1700
Data Index: 2208479 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.7785. Min Act: -0.1700
Data Index: 4505269 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.6847. Min Act: -0.1700
Data Index: 595207 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.7160. Min Act: -0.1700
Data Index: 1468171 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.6535. Min Act: -0.1700
Data Index: 3365548 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.6535. Min Act: -0.1700
Data Index: 3567771 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.6847. Min Act: -0.1700
Data Index: 7824727 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.6847. Min Act: -0.1700
Data Index: 5524168 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.6535. Min Act: -0.1700
Data Index: 5695300 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.6535. Min Act: -0.1700
Data Index: 2269992 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.6535. Min Act: -0.1700
Data Index: 2828363 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.6535. Min Act: -0.1700
Data Index: 2860274 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.6535. Min Act: -0.1700
Data Index: 4677000 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.5910. Min Act: -0.1700
Data Index: 961223 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.5910. Min Act: -0.1700
Data Index: 3252181 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.5910. Min Act: -0.1700
Data Index: 7140875 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.6222. Min Act: -0.1700
Data Index: 537956 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.5597. Min Act: -0.1700
Data Index: 1988468 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19