Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 567 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5126. Min Range: -7.5126
Max Act: 7.5126. Min Act: -0.1700
Data Index: 5765709 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5126. Min Range: -7.5126
Max Act: 7.2314. Min Act: -0.1700
Data Index: 4454127 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5126. Min Range: -7.5126
Max Act: 7.2001. Min Act: -0.1700
Data Index: 5004791 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5126. Min Range: -7.5126
Max Act: 7.0751. Min Act: -0.1700
Data Index: 8469350 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5126. Min Range: -7.5126
Max Act: 7.0751. Min Act: -0.1700
Data Index: 5929044 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5126. Min Range: -7.5126
Max Act: 7.0439. Min Act: -0.1700
Data Index: 8785626 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5126. Min Range: -7.5126
Max Act: 7.0751. Min Act: -0.1700
Data Index: 3570248 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5126. Min Range: -7.5126
Max Act: 7.0439. Min Act: -0.1700
Data Index: 5350359 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5126. Min Range: -7.5126
Max Act: 7.0439. Min Act: -0.1700
Data Index: 4351405 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5126. Min Range: -7.5126
Max Act: 7.0439. Min Act: -0.1700
Data Index: 8455911 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5126. Min Range: -7.5126
Max Act: 6.9501. Min Act: -0.1700
Data Index: 3079460 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5126. Min Range: -7.5126
Max Act: 6.9501. Min Act: -0.1700
Data Index: 3570249 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5126. Min Range: -7.5126
Max Act: 6.9189. Min Act: -0.1700
Data Index: 6200464 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5126. Min Range: -7.5126
Max Act: 6.9189. Min Act: -0.1700
Data Index: 2603510 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5126. Min Range: -7.5126
Max Act: 6.8876. Min Act: -0.1700
Data Index: 4922013 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5126. Min Range: -7.5126
Max Act: 6.8564. Min Act: -0.1700
Data Index: 5918811 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5126. Min Range: -7.5126
Max Act: 6.8251. Min Act: -0.1700
Data Index: 3327724 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5126. Min Range: -7.5126
Max Act: 6.7939. Min Act: -0.1700
Data Index: 8602505 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5126. Min Range: -7.5126
Max Act: 6.7939. Min Act: -0.1700
Data Index: 8531590 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5126. Min Range: -7.5126
Max Act: 6.7626. Min Act: -0.1700
Data Index: 1102047 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #19