Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3766 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.6719. Min Act: -0.1700
Data Index: 8481902 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.5156. Min Act: -0.1700
Data Index: 4918762 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.4531. Min Act: -0.1700
Data Index: 8025735 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.3906. Min Act: -0.1700
Data Index: 6186137 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.3906. Min Act: -0.1700
Data Index: 4055721 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.3594. Min Act: -0.1700
Data Index: 2757697 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.3594. Min Act: -0.1700
Data Index: 8157067 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.2656. Min Act: -0.1700
Data Index: 6941337 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.2656. Min Act: -0.1700
Data Index: 2895349 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.2656. Min Act: -0.1700
Data Index: 6941547 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.2343. Min Act: -0.1700
Data Index: 2661075 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.2343. Min Act: -0.1700
Data Index: 2757696 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.2031. Min Act: -0.1700
Data Index: 3097513 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.2031. Min Act: -0.1700
Data Index: 6092432 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.2031. Min Act: -0.1700
Data Index: 3739762 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.1718. Min Act: -0.1700
Data Index: 5774460 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.1718. Min Act: -0.1700
Data Index: 2757699 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.1718. Min Act: -0.1700
Data Index: 5586547 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.1406. Min Act: -0.1700
Data Index: 3282332 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.1093. Min Act: -0.1700
Data Index: 2661076 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19