Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 981 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3442. Min Range: -5.3442
Max Act: 5.3442. Min Act: -0.1700
Data Index: 6628803 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3442. Min Range: -5.3442
Max Act: 5.2192. Min Act: -0.1700
Data Index: 633599 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3442. Min Range: -5.3442
Max Act: 5.0942. Min Act: -0.1700
Data Index: 935733 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3442. Min Range: -5.3442
Max Act: 5.0630. Min Act: -0.1700
Data Index: 642878 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3442. Min Range: -5.3442
Max Act: 5.0630. Min Act: -0.1700
Data Index: 29568 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3442. Min Range: -5.3442
Max Act: 5.0630. Min Act: -0.1700
Data Index: 5192960 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3442. Min Range: -5.3442
Max Act: 5.0317. Min Act: -0.1700
Data Index: 1352604 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3442. Min Range: -5.3442
Max Act: 5.0317. Min Act: -0.1700
Data Index: 784332 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3442. Min Range: -5.3442
Max Act: 5.0005. Min Act: -0.1700
Data Index: 3529699 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3442. Min Range: -5.3442
Max Act: 4.9692. Min Act: -0.1700
Data Index: 1477139 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3442. Min Range: -5.3442
Max Act: 5.0005. Min Act: -0.1700
Data Index: 1239794 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3442. Min Range: -5.3442
Max Act: 4.9380. Min Act: -0.1700
Data Index: 4983073 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3442. Min Range: -5.3442
Max Act: 4.9380. Min Act: -0.1700
Data Index: 8393296 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3442. Min Range: -5.3442
Max Act: 4.9380. Min Act: -0.1700
Data Index: 6993835 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3442. Min Range: -5.3442
Max Act: 4.9380. Min Act: -0.1700
Data Index: 515186 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3442. Min Range: -5.3442
Max Act: 4.9380. Min Act: -0.1700
Data Index: 6835576 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3442. Min Range: -5.3442
Max Act: 4.9067. Min Act: -0.1700
Data Index: 1556465 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3442. Min Range: -5.3442
Max Act: 4.8755. Min Act: -0.1700
Data Index: 1013509 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3442. Min Range: -5.3442
Max Act: 4.9067. Min Act: -0.1700
Data Index: 3098229 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3442. Min Range: -5.3442
Max Act: 4.9067. Min Act: -0.1700
Data Index: 6628802 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19