Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1209 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4141. Min Range: -8.4141
Max Act: 8.4141. Min Act: -0.1700
Data Index: 2627368 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4141. Min Range: -8.4141
Max Act: 8.1641. Min Act: -0.1700
Data Index: 2033436 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4141. Min Range: -8.4141
Max Act: 8.1641. Min Act: -0.1700
Data Index: 7064315 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4141. Min Range: -8.4141
Max Act: 8.1641. Min Act: -0.1700
Data Index: 7064314 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4141. Min Range: -8.4141
Max Act: 8.1016. Min Act: -0.1700
Data Index: 7331428 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4141. Min Range: -8.4141
Max Act: 8.0391. Min Act: -0.1700
Data Index: 1574180 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4141. Min Range: -8.4141
Max Act: 8.1016. Min Act: -0.1700
Data Index: 4347321 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4141. Min Range: -8.4141
Max Act: 7.9766. Min Act: -0.1700
Data Index: 6554053 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4141. Min Range: -8.4141
Max Act: 7.9766. Min Act: -0.1700
Data Index: 6940665 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4141. Min Range: -8.4141
Max Act: 7.9454. Min Act: -0.1700
Data Index: 4709927 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4141. Min Range: -8.4141
Max Act: 7.9141. Min Act: -0.1700
Data Index: 1704443 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4141. Min Range: -8.4141
Max Act: 7.9141. Min Act: -0.1700
Data Index: 3708361 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4141. Min Range: -8.4141
Max Act: 7.8829. Min Act: -0.1700
Data Index: 6028615 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4141. Min Range: -8.4141
Max Act: 7.8516. Min Act: -0.1700
Data Index: 2664454 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4141. Min Range: -8.4141
Max Act: 7.8516. Min Act: -0.1700
Data Index: 7065673 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4141. Min Range: -8.4141
Max Act: 7.7891. Min Act: -0.1700
Data Index: 1953843 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4141. Min Range: -8.4141
Max Act: 7.7579. Min Act: -0.1700
Data Index: 6135145 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4141. Min Range: -8.4141
Max Act: 7.7579. Min Act: -0.1700
Data Index: 5723832 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4141. Min Range: -8.4141
Max Act: 7.7266. Min Act: -0.1700
Data Index: 4156141 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4141. Min Range: -8.4141
Max Act: 7.7891. Min Act: -0.1700
Data Index: 2376187 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19