Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 459 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0821. Min Range: -5.0821
Max Act: 5.0821. Min Act: -0.1700
Data Index: 3815381 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0821. Min Range: -5.0821
Max Act: 5.0821. Min Act: -0.1700
Data Index: 6726525 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0821. Min Range: -5.0821
Max Act: 5.0196. Min Act: -0.1700
Data Index: 872382 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0821. Min Range: -5.0821
Max Act: 5.0196. Min Act: -0.1700
Data Index: 4002 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0821. Min Range: -5.0821
Max Act: 4.9571. Min Act: -0.1700
Data Index: 7668120 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0821. Min Range: -5.0821
Max Act: 4.9571. Min Act: -0.1700
Data Index: 2745943 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0821. Min Range: -5.0821
Max Act: 4.9259. Min Act: -0.1700
Data Index: 5074460 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0821. Min Range: -5.0821
Max Act: 4.8946. Min Act: -0.1700
Data Index: 6386830 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0821. Min Range: -5.0821
Max Act: 4.8946. Min Act: -0.1700
Data Index: 6834611 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0821. Min Range: -5.0821
Max Act: 4.8321. Min Act: -0.1700
Data Index: 5351879 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0821. Min Range: -5.0821
Max Act: 4.8321. Min Act: -0.1700
Data Index: 4998474 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0821. Min Range: -5.0821
Max Act: 4.8321. Min Act: -0.1700
Data Index: 2733801 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0821. Min Range: -5.0821
Max Act: 4.8009. Min Act: -0.1700
Data Index: 5785818 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0821. Min Range: -5.0821
Max Act: 4.7696. Min Act: -0.1700
Data Index: 287842 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0821. Min Range: -5.0821
Max Act: 4.7696. Min Act: -0.1700
Data Index: 849651 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0821. Min Range: -5.0821
Max Act: 4.7696. Min Act: -0.1700
Data Index: 986598 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0821. Min Range: -5.0821
Max Act: 4.7696. Min Act: -0.1700
Data Index: 6653498 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0821. Min Range: -5.0821
Max Act: 4.7384. Min Act: -0.1700
Data Index: 4037882 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0821. Min Range: -5.0821
Max Act: 4.7384. Min Act: -0.1700
Data Index: 951700 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0821. Min Range: -5.0821
Max Act: 4.7384. Min Act: -0.1700
Data Index: 1790856 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19