Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2782 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6703. Min Range: -7.6703
Max Act: 7.6703. Min Act: -0.1700
Data Index: 2404149 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6703. Min Range: -7.6703
Max Act: 7.6391. Min Act: -0.1700
Data Index: 1249062 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6703. Min Range: -7.6703
Max Act: 7.6078. Min Act: -0.1700
Data Index: 3215513 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6703. Min Range: -7.6703
Max Act: 7.3266. Min Act: -0.1700
Data Index: 728691 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6703. Min Range: -7.6703
Max Act: 7.3266. Min Act: -0.1700
Data Index: 6418368 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6703. Min Range: -7.6703
Max Act: 7.2641. Min Act: -0.1700
Data Index: 3083814 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6703. Min Range: -7.6703
Max Act: 7.2328. Min Act: -0.1700
Data Index: 3709382 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6703. Min Range: -7.6703
Max Act: 7.2641. Min Act: -0.1700
Data Index: 3161300 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6703. Min Range: -7.6703
Max Act: 7.2016. Min Act: -0.1700
Data Index: 6018250 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6703. Min Range: -7.6703
Max Act: 7.1703. Min Act: -0.1700
Data Index: 5634486 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6703. Min Range: -7.6703
Max Act: 7.1703. Min Act: -0.1700
Data Index: 4374002 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6703. Min Range: -7.6703
Max Act: 7.1703. Min Act: -0.1700
Data Index: 1395618 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6703. Min Range: -7.6703
Max Act: 7.1391. Min Act: -0.1700
Data Index: 6209533 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6703. Min Range: -7.6703
Max Act: 7.1078. Min Act: -0.1700
Data Index: 7530296 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6703. Min Range: -7.6703
Max Act: 7.1078. Min Act: -0.1700
Data Index: 2909997 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6703. Min Range: -7.6703
Max Act: 7.0766. Min Act: -0.1700
Data Index: 3118141 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6703. Min Range: -7.6703
Max Act: 7.0453. Min Act: -0.1700
Data Index: 2980451 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6703. Min Range: -7.6703
Max Act: 7.0453. Min Act: -0.1700
Data Index: 2344228 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6703. Min Range: -7.6703
Max Act: 6.9828. Min Act: -0.1700
Data Index: 6564444 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6703. Min Range: -7.6703
Max Act: 7.0141. Min Act: -0.1700
Data Index: 4494947 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19