Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3100 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7169. Min Range: -4.7169
Max Act: 4.7169. Min Act: -0.1700
Data Index: 6700036 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7169. Min Range: -4.7169
Max Act: 4.5919. Min Act: -0.1700
Data Index: 7903457 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7169. Min Range: -4.7169
Max Act: 4.5919. Min Act: -0.1700
Data Index: 613045 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7169. Min Range: -4.7169
Max Act: 4.5919. Min Act: -0.1700
Data Index: 5956401 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7169. Min Range: -4.7169
Max Act: 4.5606. Min Act: -0.1700
Data Index: 6647341 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7169. Min Range: -4.7169
Max Act: 4.5294. Min Act: -0.1700
Data Index: 5266505 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7169. Min Range: -4.7169
Max Act: 4.4981. Min Act: -0.1700
Data Index: 34038 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7169. Min Range: -4.7169
Max Act: 4.5294. Min Act: -0.1700
Data Index: 1806147 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7169. Min Range: -4.7169
Max Act: 4.4981. Min Act: -0.1700
Data Index: 8438798 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7169. Min Range: -4.7169
Max Act: 4.4981. Min Act: -0.1700
Data Index: 4919076 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7169. Min Range: -4.7169
Max Act: 4.4669. Min Act: -0.1700
Data Index: 8724156 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7169. Min Range: -4.7169
Max Act: 4.4669. Min Act: -0.1700
Data Index: 6564144 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7169. Min Range: -4.7169
Max Act: 4.4669. Min Act: -0.1700
Data Index: 4288449 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7169. Min Range: -4.7169
Max Act: 4.4669. Min Act: -0.1700
Data Index: 4239885 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7169. Min Range: -4.7169
Max Act: 4.4669. Min Act: -0.1700
Data Index: 889704 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7169. Min Range: -4.7169
Max Act: 4.4356. Min Act: -0.1700
Data Index: 3347501 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7169. Min Range: -4.7169
Max Act: 4.4044. Min Act: -0.1700
Data Index: 631036 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7169. Min Range: -4.7169
Max Act: 4.3419. Min Act: -0.1700
Data Index: 1333412 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7169. Min Range: -4.7169
Max Act: 4.3731. Min Act: -0.1700
Data Index: 2990526 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7169. Min Range: -4.7169
Max Act: 4.3419. Min Act: -0.1700
Data Index: 4913264 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19