Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1652 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6154. Min Range: -8.6154
Max Act: 8.6154. Min Act: -0.1700
Data Index: 8512112 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6154. Min Range: -8.6154
Max Act: 8.5529. Min Act: -0.1700
Data Index: 1084664 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6154. Min Range: -8.6154
Max Act: 8.4279. Min Act: -0.1700
Data Index: 8635958 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6154. Min Range: -8.6154
Max Act: 8.2404. Min Act: -0.1700
Data Index: 2661445 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6154. Min Range: -8.6154
Max Act: 8.3029. Min Act: -0.1700
Data Index: 7382711 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6154. Min Range: -8.6154
Max Act: 8.1779. Min Act: -0.1700
Data Index: 229070 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6154. Min Range: -8.6154
Max Act: 8.1779. Min Act: -0.1700
Data Index: 5430521 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6154. Min Range: -8.6154
Max Act: 8.1779. Min Act: -0.1700
Data Index: 4609007 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6154. Min Range: -8.6154
Max Act: 8.0529. Min Act: -0.1700
Data Index: 4426159 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6154. Min Range: -8.6154
Max Act: 7.9279. Min Act: -0.1700
Data Index: 8005277 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6154. Min Range: -8.6154
Max Act: 7.9904. Min Act: -0.1700
Data Index: 878371 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6154. Min Range: -8.6154
Max Act: 7.9904. Min Act: -0.1700
Data Index: 2758997 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6154. Min Range: -8.6154
Max Act: 7.9279. Min Act: -0.1700
Data Index: 5723832 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6154. Min Range: -8.6154
Max Act: 7.9279. Min Act: -0.1700
Data Index: 8397739 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6154. Min Range: -8.6154
Max Act: 7.9279. Min Act: -0.1700
Data Index: 3223 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6154. Min Range: -8.6154
Max Act: 7.9279. Min Act: -0.1700
Data Index: 2725914 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6154. Min Range: -8.6154
Max Act: 7.9279. Min Act: -0.1700
Data Index: 3317852 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6154. Min Range: -8.6154
Max Act: 7.9279. Min Act: -0.1700
Data Index: 2195011 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6154. Min Range: -8.6154
Max Act: 7.8654. Min Act: -0.1700
Data Index: 5704670 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6154. Min Range: -8.6154
Max Act: 7.8654. Min Act: -0.1700
Data Index: 4815582 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19