Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3459 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1388. Min Range: -4.1388
Max Act: 4.1388. Min Act: -0.1700
Data Index: 108442 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1388. Min Range: -4.1388
Max Act: 4.0137. Min Act: -0.1700
Data Index: 4433053 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1388. Min Range: -4.1388
Max Act: 3.9825. Min Act: -0.1700
Data Index: 3528980 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1388. Min Range: -4.1388
Max Act: 3.9825. Min Act: -0.1700
Data Index: 4532359 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1388. Min Range: -4.1388
Max Act: 3.9512. Min Act: -0.1700
Data Index: 2372480 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1388. Min Range: -4.1388
Max Act: 3.9512. Min Act: -0.1700
Data Index: 2982352 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1388. Min Range: -4.1388
Max Act: 3.9512. Min Act: -0.1700
Data Index: 2831477 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1388. Min Range: -4.1388
Max Act: 3.9512. Min Act: -0.1700
Data Index: 2634482 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1388. Min Range: -4.1388
Max Act: 3.9512. Min Act: -0.1700
Data Index: 639447 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1388. Min Range: -4.1388
Max Act: 3.9199. Min Act: -0.1700
Data Index: 6486528 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1388. Min Range: -4.1388
Max Act: 3.9199. Min Act: -0.1700
Data Index: 2982350 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1388. Min Range: -4.1388
Max Act: 3.9199. Min Act: -0.1700
Data Index: 6195311 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1388. Min Range: -4.1388
Max Act: 3.8887. Min Act: -0.1700
Data Index: 8431896 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1388. Min Range: -4.1388
Max Act: 3.8574. Min Act: -0.1700
Data Index: 1720388 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1388. Min Range: -4.1388
Max Act: 3.8887. Min Act: -0.1700
Data Index: 6237963 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1388. Min Range: -4.1388
Max Act: 3.8887. Min Act: -0.1700
Data Index: 3796 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1388. Min Range: -4.1388
Max Act: 3.8887. Min Act: -0.1700
Data Index: 6958859 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1388. Min Range: -4.1388
Max Act: 3.8887. Min Act: -0.1700
Data Index: 1372966 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1388. Min Range: -4.1388
Max Act: 3.8887. Min Act: -0.1700
Data Index: 2831470 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1388. Min Range: -4.1388
Max Act: 3.8887. Min Act: -0.1700
Data Index: 255372 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19