Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1165 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3720. Min Range: -7.3720
Max Act: 7.3720. Min Act: -0.1700
Data Index: 4480814 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3720. Min Range: -7.3720
Max Act: 7.3095. Min Act: -0.1700
Data Index: 1510706 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3720. Min Range: -7.3720
Max Act: 6.9970. Min Act: -0.1700
Data Index: 4480810 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3720. Min Range: -7.3720
Max Act: 6.8720. Min Act: -0.1700
Data Index: 1960454 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3720. Min Range: -7.3720
Max Act: 6.7783. Min Act: -0.1700
Data Index: 4263864 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3720. Min Range: -7.3720
Max Act: 6.6220. Min Act: -0.1700
Data Index: 301791 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3720. Min Range: -7.3720
Max Act: 6.5595. Min Act: -0.1700
Data Index: 6401158 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3720. Min Range: -7.3720
Max Act: 6.5283. Min Act: -0.1700
Data Index: 6566185 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3720. Min Range: -7.3720
Max Act: 6.4970. Min Act: -0.1700
Data Index: 2390616 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3720. Min Range: -7.3720
Max Act: 6.4658. Min Act: -0.1700
Data Index: 2886305 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3720. Min Range: -7.3720
Max Act: 6.4658. Min Act: -0.1700
Data Index: 6069886 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3720. Min Range: -7.3720
Max Act: 6.4345. Min Act: -0.1700
Data Index: 6691955 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3720. Min Range: -7.3720
Max Act: 6.4345. Min Act: -0.1700
Data Index: 3819439 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3720. Min Range: -7.3720
Max Act: 6.3720. Min Act: -0.1700
Data Index: 3655957 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3720. Min Range: -7.3720
Max Act: 6.3720. Min Act: -0.1700
Data Index: 6691952 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3720. Min Range: -7.3720
Max Act: 6.4033. Min Act: -0.1700
Data Index: 17392 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3720. Min Range: -7.3720
Max Act: 6.4033. Min Act: -0.1700
Data Index: 869452 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3720. Min Range: -7.3720
Max Act: 6.3720. Min Act: -0.1700
Data Index: 5317271 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3720. Min Range: -7.3720
Max Act: 6.3720. Min Act: -0.1700
Data Index: 1593301 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3720. Min Range: -7.3720
Max Act: 6.3408. Min Act: -0.1700
Data Index: 5033277 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #19