Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2806 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0406. Min Range: -5.0406
Max Act: 5.0406. Min Act: -0.1700
Data Index: 8652955 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.9156. Min Act: -0.1700
Data Index: 2636442 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.8531. Min Act: -0.1700
Data Index: 4701410 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.8531. Min Act: -0.1700
Data Index: 2842989 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.7906. Min Act: -0.1700
Data Index: 7646574 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.7594. Min Act: -0.1700
Data Index: 6173335 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.7594. Min Act: -0.1700
Data Index: 32873 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.7594. Min Act: -0.1700
Data Index: 4291923 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.7594. Min Act: -0.1700
Data Index: 8561634 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.7281. Min Act: -0.1700
Data Index: 960023 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.7281. Min Act: -0.1700
Data Index: 2861506 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.7281. Min Act: -0.1700
Data Index: 4311550 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.7594. Min Act: -0.1700
Data Index: 2624475 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.7281. Min Act: -0.1700
Data Index: 2771318 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.6656. Min Act: -0.1700
Data Index: 5320440 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.6969. Min Act: -0.1700
Data Index: 3664309 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.6969. Min Act: -0.1700
Data Index: 1277341 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.6969. Min Act: -0.1700
Data Index: 1863281 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.6969. Min Act: -0.1700
Data Index: 3206493 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.6969. Min Act: -0.1700
Data Index: 3915772 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19