Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9765. Min Range: -2.9765
Max Act: 2.9765. Min Act: -0.1700
Data Index: 3214991 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9765. Min Range: -2.9765
Max Act: 2.7701. Min Act: -0.1700
Data Index: 3498795 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9765. Min Range: -2.9765
Max Act: 2.7701. Min Act: -0.1700
Data Index: 7915931 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9765. Min Range: -2.9765
Max Act: 2.6582. Min Act: -0.1700
Data Index: 5639897 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9765. Min Range: -2.9765
Max Act: 2.6902. Min Act: -0.1700
Data Index: 5313831 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9765. Min Range: -2.9765
Max Act: 2.6100. Min Act: -0.1700
Data Index: 4010126 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9765. Min Range: -2.9765
Max Act: 2.6261. Min Act: -0.1700
Data Index: 6162248 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9765. Min Range: -2.9765
Max Act: 2.5455. Min Act: -0.1700
Data Index: 8742802 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9765. Min Range: -2.9765
Max Act: 2.5617. Min Act: -0.1700
Data Index: 1344947 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9765. Min Range: -2.9765
Max Act: 2.5778. Min Act: -0.1700
Data Index: 7347107 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9765. Min Range: -2.9765
Max Act: 2.6261. Min Act: -0.1700
Data Index: 2068974 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9765. Min Range: -2.9765
Max Act: 2.5778. Min Act: -0.1700
Data Index: 8661233 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9765. Min Range: -2.9765
Max Act: 2.6100. Min Act: -0.1700
Data Index: 4225947 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9765. Min Range: -2.9765
Max Act: 2.6742. Min Act: -0.1700
Data Index: 1589532 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9765. Min Range: -2.9765
Max Act: 2.5132. Min Act: -0.1700
Data Index: 7900007 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9765. Min Range: -2.9765
Max Act: 2.5617. Min Act: -0.1700
Data Index: 306145 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9765. Min Range: -2.9765
Max Act: 2.6100. Min Act: -0.1700
Data Index: 506425 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9765. Min Range: -2.9765
Max Act: 2.5455. Min Act: -0.1700
Data Index: 3245672 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9765. Min Range: -2.9765
Max Act: 2.5939. Min Act: -0.1700
Data Index: 8262572 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9765. Min Range: -2.9765
Max Act: 2.5778. Min Act: -0.1700
Data Index: 4519690 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19