Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3439 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.3844. Min Range: -2.3844
Max Act: 2.3844. Min Act: -0.1700
Data Index: 2474673 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3844. Min Range: -2.3844
Max Act: 2.3680. Min Act: -0.1700
Data Index: 2213801 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3844. Min Range: -2.3844
Max Act: 2.3024. Min Act: -0.1700
Data Index: 194889 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3844. Min Range: -2.3844
Max Act: 2.2529. Min Act: -0.1700
Data Index: 685327 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3844. Min Range: -2.3844
Max Act: 2.2364. Min Act: -0.1700
Data Index: 3032911 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3844. Min Range: -2.3844
Max Act: 2.2199. Min Act: -0.1700
Data Index: 7834710 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3844. Min Range: -2.3844
Max Act: 2.2364. Min Act: -0.1700
Data Index: 4328224 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3844. Min Range: -2.3844
Max Act: 2.2199. Min Act: -0.1700
Data Index: 6063554 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3844. Min Range: -2.3844
Max Act: 2.2033. Min Act: -0.1700
Data Index: 350260 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3844. Min Range: -2.3844
Max Act: 2.2033. Min Act: -0.1696
Data Index: 2183103 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3844. Min Range: -2.3844
Max Act: 2.1701. Min Act: -0.1700
Data Index: 3586580 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3844. Min Range: -2.3844
Max Act: 2.1701. Min Act: -0.1699
Data Index: 4761902 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3844. Min Range: -2.3844
Max Act: 2.1701. Min Act: -0.1700
Data Index: 4768555 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3844. Min Range: -2.3844
Max Act: 2.1534. Min Act: -0.1700
Data Index: 6286409 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3844. Min Range: -2.3844
Max Act: 2.1534. Min Act: -0.1700
Data Index: 4063291 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3844. Min Range: -2.3844
Max Act: 2.1367. Min Act: -0.1700
Data Index: 8209784 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3844. Min Range: -2.3844
Max Act: 2.1367. Min Act: -0.1700
Data Index: 4260647 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3844. Min Range: -2.3844
Max Act: 2.1367. Min Act: -0.1700
Data Index: 71670 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3844. Min Range: -2.3844
Max Act: 2.1534. Min Act: -0.1700
Data Index: 7817160 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3844. Min Range: -2.3844
Max Act: 2.1367. Min Act: -0.1700
Data Index: 6017449 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19