Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2028 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0162. Min Range: -7.0162
Max Act: 7.0162. Min Act: -0.1700
Data Index: 1114741 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0162. Min Range: -7.0162
Max Act: 6.7662. Min Act: -0.1700
Data Index: 5667953 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0162. Min Range: -7.0162
Max Act: 6.7037. Min Act: -0.1700
Data Index: 7552023 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0162. Min Range: -7.0162
Max Act: 6.7037. Min Act: -0.1700
Data Index: 4283566 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0162. Min Range: -7.0162
Max Act: 6.6412. Min Act: -0.1700
Data Index: 2821171 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0162. Min Range: -7.0162
Max Act: 6.6412. Min Act: -0.1700
Data Index: 6463089 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0162. Min Range: -7.0162
Max Act: 6.5475. Min Act: -0.1700
Data Index: 4372577 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0162. Min Range: -7.0162
Max Act: 6.5162. Min Act: -0.1700
Data Index: 8074949 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0162. Min Range: -7.0162
Max Act: 6.4850. Min Act: -0.1700
Data Index: 1372137 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0162. Min Range: -7.0162
Max Act: 6.4850. Min Act: -0.1700
Data Index: 4545211 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0162. Min Range: -7.0162
Max Act: 6.4537. Min Act: -0.1700
Data Index: 915938 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0162. Min Range: -7.0162
Max Act: 6.4537. Min Act: -0.1700
Data Index: 6198579 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0162. Min Range: -7.0162
Max Act: 6.4225. Min Act: -0.1700
Data Index: 2364356 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0162. Min Range: -7.0162
Max Act: 6.4225. Min Act: -0.1700
Data Index: 2309125 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0162. Min Range: -7.0162
Max Act: 6.4225. Min Act: -0.1700
Data Index: 6190459 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0162. Min Range: -7.0162
Max Act: 6.3912. Min Act: -0.1700
Data Index: 1702832 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0162. Min Range: -7.0162
Max Act: 6.4225. Min Act: -0.1700
Data Index: 7118927 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0162. Min Range: -7.0162
Max Act: 6.3287. Min Act: -0.1700
Data Index: 5180723 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0162. Min Range: -7.0162
Max Act: 6.3600. Min Act: -0.1700
Data Index: 3907959 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0162. Min Range: -7.0162
Max Act: 6.3600. Min Act: -0.1700
Data Index: 512268 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19