Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2712 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5944. Min Range: -9.5944
Max Act: 9.5944. Min Act: -0.1700
Data Index: 7503202 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5944. Min Range: -9.5944
Max Act: 9.4694. Min Act: -0.1700
Data Index: 5700937 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5944. Min Range: -9.5944
Max Act: 9.4069. Min Act: -0.1700
Data Index: 485575 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5944. Min Range: -9.5944
Max Act: 9.3444. Min Act: -0.1700
Data Index: 5615549 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5944. Min Range: -9.5944
Max Act: 9.2819. Min Act: -0.1700
Data Index: 7327053 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5944. Min Range: -9.5944
Max Act: 9.1569. Min Act: -0.1700
Data Index: 3209670 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5944. Min Range: -9.5944
Max Act: 9.1569. Min Act: -0.1700
Data Index: 5948673 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5944. Min Range: -9.5944
Max Act: 9.0944. Min Act: -0.1700
Data Index: 2557879 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5944. Min Range: -9.5944
Max Act: 9.1569. Min Act: -0.1700
Data Index: 906199 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5944. Min Range: -9.5944
Max Act: 9.0944. Min Act: -0.1700
Data Index: 5700344 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5944. Min Range: -9.5944
Max Act: 8.9694. Min Act: -0.1700
Data Index: 5656544 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5944. Min Range: -9.5944
Max Act: 8.9069. Min Act: -0.1700
Data Index: 6694564 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5944. Min Range: -9.5944
Max Act: 8.9069. Min Act: -0.1700
Data Index: 4210373 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5944. Min Range: -9.5944
Max Act: 8.9069. Min Act: -0.1700
Data Index: 2001408 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5944. Min Range: -9.5944
Max Act: 8.9069. Min Act: -0.1700
Data Index: 1406691 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5944. Min Range: -9.5944
Max Act: 8.8444. Min Act: -0.1700
Data Index: 256837 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5944. Min Range: -9.5944
Max Act: 8.8444. Min Act: -0.1700
Data Index: 116108 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5944. Min Range: -9.5944
Max Act: 8.8444. Min Act: -0.1700
Data Index: 5360435 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5944. Min Range: -9.5944
Max Act: 8.8444. Min Act: -0.1700
Data Index: 906219 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5944. Min Range: -9.5944
Max Act: 8.9069. Min Act: -0.1700
Data Index: 3228106 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19