Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4849 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.2896. Min Range: -2.2896
Max Act: 2.2896. Min Act: -0.1700
Data Index: 8829176 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2896. Min Range: -2.2896
Max Act: 2.2566. Min Act: -0.1700
Data Index: 705233 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2896. Min Range: -2.2896
Max Act: 2.2070. Min Act: -0.1700
Data Index: 4927322 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2896. Min Range: -2.2896
Max Act: 2.1904. Min Act: -0.1700
Data Index: 7172993 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2896. Min Range: -2.2896
Max Act: 2.1738. Min Act: -0.1700
Data Index: 4071641 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2896. Min Range: -2.2896
Max Act: 2.1904. Min Act: -0.1700
Data Index: 174835 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2896. Min Range: -2.2896
Max Act: 2.1738. Min Act: -0.1700
Data Index: 3543062 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2896. Min Range: -2.2896
Max Act: 2.1738. Min Act: -0.1700
Data Index: 8553987 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2896. Min Range: -2.2896
Max Act: 2.1571. Min Act: -0.1700
Data Index: 375987 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2896. Min Range: -2.2896
Max Act: 2.1571. Min Act: -0.1700
Data Index: 4158060 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2896. Min Range: -2.2896
Max Act: 2.1571. Min Act: -0.1700
Data Index: 8479035 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2896. Min Range: -2.2896
Max Act: 2.1405. Min Act: -0.1700
Data Index: 1484524 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2896. Min Range: -2.2896
Max Act: 2.1405. Min Act: -0.1700
Data Index: 129346 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2896. Min Range: -2.2896
Max Act: 2.1405. Min Act: -0.1700
Data Index: 539405 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2896. Min Range: -2.2896
Max Act: 2.1238. Min Act: -0.1700
Data Index: 5794318 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2896. Min Range: -2.2896
Max Act: 2.1405. Min Act: -0.1700
Data Index: 7762488 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2896. Min Range: -2.2896
Max Act: 2.1238. Min Act: -0.1700
Data Index: 4494762 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2896. Min Range: -2.2896
Max Act: 2.1238. Min Act: -0.1700
Data Index: 6227189 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2896. Min Range: -2.2896
Max Act: 2.1238. Min Act: -0.1700
Data Index: 2526853 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2896. Min Range: -2.2896
Max Act: 2.1070. Min Act: -0.1700
Data Index: 7188672 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19