Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4340 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.0881. Min Range: -11.0881
Max Act: 11.0881. Min Act: -0.1700
Data Index: 1569816 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0881. Min Range: -11.0881
Max Act: 10.7756. Min Act: -0.1700
Data Index: 85618 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0881. Min Range: -11.0881
Max Act: 10.5256. Min Act: -0.1700
Data Index: 1367004 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0881. Min Range: -11.0881
Max Act: 10.3381. Min Act: -0.1700
Data Index: 7099543 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0881. Min Range: -11.0881
Max Act: 10.2756. Min Act: -0.1700
Data Index: 8699919 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0881. Min Range: -11.0881
Max Act: 10.2756. Min Act: -0.1700
Data Index: 8119985 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0881. Min Range: -11.0881
Max Act: 10.2756. Min Act: -0.1700
Data Index: 3019537 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0881. Min Range: -11.0881
Max Act: 10.2131. Min Act: -0.1700
Data Index: 4672140 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0881. Min Range: -11.0881
Max Act: 10.1506. Min Act: -0.1700
Data Index: 7946413 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0881. Min Range: -11.0881
Max Act: 10.1506. Min Act: -0.1700
Data Index: 1774439 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0881. Min Range: -11.0881
Max Act: 10.2131. Min Act: -0.1700
Data Index: 5212697 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0881. Min Range: -11.0881
Max Act: 10.0881. Min Act: -0.1700
Data Index: 8052103 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0881. Min Range: -11.0881
Max Act: 10.0881. Min Act: -0.1700
Data Index: 6832116 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0881. Min Range: -11.0881
Max Act: 10.0881. Min Act: -0.1700
Data Index: 5816916 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0881. Min Range: -11.0881
Max Act: 10.0881. Min Act: -0.1700
Data Index: 5989306 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0881. Min Range: -11.0881
Max Act: 10.0881. Min Act: -0.1700
Data Index: 7889351 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0881. Min Range: -11.0881
Max Act: 10.0256. Min Act: -0.1700
Data Index: 6297207 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0881. Min Range: -11.0881
Max Act: 10.0256. Min Act: -0.1700
Data Index: 6375593 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0881. Min Range: -11.0881
Max Act: 10.0256. Min Act: -0.1700
Data Index: 4390642 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0881. Min Range: -11.0881
Max Act: 10.0256. Min Act: -0.1700
Data Index: 4093671 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19