Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3304 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8252. Min Range: -5.8252
Max Act: 5.8252. Min Act: -0.1700
Data Index: 5814855 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8252. Min Range: -5.8252
Max Act: 5.7939. Min Act: -0.1700
Data Index: 4423716 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8252. Min Range: -5.8252
Max Act: 5.8252. Min Act: -0.1700
Data Index: 2276019 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8252. Min Range: -5.8252
Max Act: 5.7627. Min Act: -0.1700
Data Index: 204188 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8252. Min Range: -5.8252
Max Act: 5.7627. Min Act: -0.1700
Data Index: 5340377 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8252. Min Range: -5.8252
Max Act: 5.7314. Min Act: -0.1700
Data Index: 1315733 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8252. Min Range: -5.8252
Max Act: 5.7314. Min Act: -0.1700
Data Index: 1347904 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8252. Min Range: -5.8252
Max Act: 5.7002. Min Act: -0.1700
Data Index: 5326254 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8252. Min Range: -5.8252
Max Act: 5.6689. Min Act: -0.1700
Data Index: 6857354 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8252. Min Range: -5.8252
Max Act: 5.6064. Min Act: -0.1700
Data Index: 3116622 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8252. Min Range: -5.8252
Max Act: 5.6689. Min Act: -0.1700
Data Index: 161812 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8252. Min Range: -5.8252
Max Act: 5.6377. Min Act: -0.1700
Data Index: 4718685 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8252. Min Range: -5.8252
Max Act: 5.6064. Min Act: -0.1700
Data Index: 7472078 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8252. Min Range: -5.8252
Max Act: 5.6064. Min Act: -0.1700
Data Index: 8120467 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8252. Min Range: -5.8252
Max Act: 5.6064. Min Act: -0.1700
Data Index: 4746432 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8252. Min Range: -5.8252
Max Act: 5.5752. Min Act: -0.1700
Data Index: 6465880 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8252. Min Range: -5.8252
Max Act: 5.6064. Min Act: -0.1700
Data Index: 5832058 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8252. Min Range: -5.8252
Max Act: 5.5439. Min Act: -0.1700
Data Index: 27180 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8252. Min Range: -5.8252
Max Act: 5.5439. Min Act: -0.1700
Data Index: 7835700 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8252. Min Range: -5.8252
Max Act: 5.5127. Min Act: -0.1700
Data Index: 141423 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19