Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3454 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6451. Min Range: -5.6451
Max Act: 5.6451. Min Act: -0.1700
Data Index: 4584282 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6451. Min Range: -5.6451
Max Act: 5.5826. Min Act: -0.1700
Data Index: 641518 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6451. Min Range: -5.6451
Max Act: 5.5514. Min Act: -0.1700
Data Index: 4760395 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6451. Min Range: -5.6451
Max Act: 5.5201. Min Act: -0.1700
Data Index: 1196330 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6451. Min Range: -5.6451
Max Act: 5.4889. Min Act: -0.1700
Data Index: 1318111 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6451. Min Range: -5.6451
Max Act: 5.4889. Min Act: -0.1700
Data Index: 7139175 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6451. Min Range: -5.6451
Max Act: 5.4889. Min Act: -0.1700
Data Index: 7978753 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6451. Min Range: -5.6451
Max Act: 5.4576. Min Act: -0.1698
Data Index: 6816280 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6451. Min Range: -5.6451
Max Act: 5.4264. Min Act: -0.1700
Data Index: 3651491 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6451. Min Range: -5.6451
Max Act: 5.4264. Min Act: -0.1700
Data Index: 1464436 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6451. Min Range: -5.6451
Max Act: 5.3951. Min Act: -0.1700
Data Index: 2579521 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6451. Min Range: -5.6451
Max Act: 5.4576. Min Act: -0.1690
Data Index: 6934243 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6451. Min Range: -5.6451
Max Act: 5.4264. Min Act: -0.1696
Data Index: 3584970 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6451. Min Range: -5.6451
Max Act: 5.4264. Min Act: -0.1700
Data Index: 815011 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6451. Min Range: -5.6451
Max Act: 5.3951. Min Act: -0.1700
Data Index: 5539208 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6451. Min Range: -5.6451
Max Act: 5.3951. Min Act: -0.1700
Data Index: 5578856 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6451. Min Range: -5.6451
Max Act: 5.3951. Min Act: -0.1700
Data Index: 5134803 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6451. Min Range: -5.6451
Max Act: 5.3951. Min Act: -0.1700
Data Index: 2545914 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6451. Min Range: -5.6451
Max Act: 5.4264. Min Act: -0.1700
Data Index: 5040355 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6451. Min Range: -5.6451
Max Act: 5.3951. Min Act: -0.1700
Data Index: 4062106 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19