Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3555 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9626. Min Range: -1.9626
Max Act: 1.9626. Min Act: -0.1700
Data Index: 3252324 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9626. Min Range: -1.9626
Max Act: 1.7400. Min Act: -0.1699
Data Index: 3531676 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9626. Min Range: -1.9626
Max Act: 1.7400. Min Act: -0.1689
Data Index: 3942376 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9626. Min Range: -1.9626
Max Act: 1.7227. Min Act: -0.1700
Data Index: 6738694 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9626. Min Range: -1.9626
Max Act: 1.7227. Min Act: -0.1699
Data Index: 5631982 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9626. Min Range: -1.9626
Max Act: 1.6532. Min Act: -0.1700
Data Index: 5248199 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9626. Min Range: -1.9626
Max Act: 1.6706. Min Act: -0.1700
Data Index: 1523243 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9626. Min Range: -1.9626
Max Act: 1.6532. Min Act: -0.1696
Data Index: 2029013 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9626. Min Range: -1.9626
Max Act: 1.6358. Min Act: -0.1700
Data Index: 5207630 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9626. Min Range: -1.9626
Max Act: 1.6358. Min Act: -0.1697
Data Index: 4931620 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9626. Min Range: -1.9626
Max Act: 1.6184. Min Act: -0.1700
Data Index: 5207636 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9626. Min Range: -1.9626
Max Act: 1.6009. Min Act: -0.1700
Data Index: 3810964 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9626. Min Range: -1.9626
Max Act: 1.6184. Min Act: -0.1696
Data Index: 2070708 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9626. Min Range: -1.9626
Max Act: 1.5835. Min Act: -0.1700
Data Index: 6372255 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9626. Min Range: -1.9626
Max Act: 1.5835. Min Act: -0.1698
Data Index: 7824926 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9626. Min Range: -1.9626
Max Act: 1.5835. Min Act: -0.1700
Data Index: 4079157 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9626. Min Range: -1.9626
Max Act: 1.5835. Min Act: -0.1700
Data Index: 5380430 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9626. Min Range: -1.9626
Max Act: 1.5660. Min Act: -0.1693
Data Index: 5806821 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9626. Min Range: -1.9626
Max Act: 1.5660. Min Act: -0.1700
Data Index: 3575601 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9626. Min Range: -1.9626
Max Act: 1.5660. Min Act: -0.1699
Data Index: 3575603 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19