Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4731 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9776. Min Range: -5.9776
Max Act: 5.9776. Min Act: -0.1700
Data Index: 3023081 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9776. Min Range: -5.9776
Max Act: 5.9463. Min Act: -0.1700
Data Index: 1011393 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9776. Min Range: -5.9776
Max Act: 5.6338. Min Act: -0.1700
Data Index: 8304072 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9776. Min Range: -5.9776
Max Act: 5.6026. Min Act: -0.1700
Data Index: 3735028 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9776. Min Range: -5.9776
Max Act: 5.5713. Min Act: -0.1700
Data Index: 8447401 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9776. Min Range: -5.9776
Max Act: 5.5401. Min Act: -0.1700
Data Index: 6942928 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9776. Min Range: -5.9776
Max Act: 5.5401. Min Act: -0.1700
Data Index: 4870687 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9776. Min Range: -5.9776
Max Act: 5.5401. Min Act: -0.1700
Data Index: 6463712 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9776. Min Range: -5.9776
Max Act: 5.5088. Min Act: -0.1700
Data Index: 3001953 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9776. Min Range: -5.9776
Max Act: 5.5088. Min Act: -0.1700
Data Index: 8751343 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9776. Min Range: -5.9776
Max Act: 5.4463. Min Act: -0.1700
Data Index: 1070429 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9776. Min Range: -5.9776
Max Act: 5.4776. Min Act: -0.1700
Data Index: 5380666 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9776. Min Range: -5.9776
Max Act: 5.4151. Min Act: -0.1700
Data Index: 7444376 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9776. Min Range: -5.9776
Max Act: 5.4463. Min Act: -0.1700
Data Index: 790882 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9776. Min Range: -5.9776
Max Act: 5.4463. Min Act: -0.1700
Data Index: 6275468 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9776. Min Range: -5.9776
Max Act: 5.4463. Min Act: -0.1700
Data Index: 8659057 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9776. Min Range: -5.9776
Max Act: 5.4151. Min Act: -0.1700
Data Index: 934133 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9776. Min Range: -5.9776
Max Act: 5.4151. Min Act: -0.1700
Data Index: 4218094 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9776. Min Range: -5.9776
Max Act: 5.4151. Min Act: -0.1700
Data Index: 1535189 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9776. Min Range: -5.9776
Max Act: 5.3838. Min Act: -0.1700
Data Index: 6822243 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19