Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 809 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5220. Min Range: -5.5220
Max Act: 5.5220. Min Act: -0.1700
Data Index: 4670931 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5220. Min Range: -5.5220
Max Act: 5.4283. Min Act: -0.1700
Data Index: 5679091 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5220. Min Range: -5.5220
Max Act: 5.3345. Min Act: -0.1700
Data Index: 900640 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5220. Min Range: -5.5220
Max Act: 5.3345. Min Act: -0.1700
Data Index: 4945873 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5220. Min Range: -5.5220
Max Act: 5.3033. Min Act: -0.1700
Data Index: 7196778 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5220. Min Range: -5.5220
Max Act: 5.2720. Min Act: -0.1700
Data Index: 7148035 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5220. Min Range: -5.5220
Max Act: 5.2720. Min Act: -0.1700
Data Index: 5448941 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5220. Min Range: -5.5220
Max Act: 5.2095. Min Act: -0.1700
Data Index: 5899418 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5220. Min Range: -5.5220
Max Act: 5.2095. Min Act: -0.1700
Data Index: 1862301 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5220. Min Range: -5.5220
Max Act: 5.1783. Min Act: -0.1700
Data Index: 7196776 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5220. Min Range: -5.5220
Max Act: 5.1158. Min Act: -0.1700
Data Index: 852557 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5220. Min Range: -5.5220
Max Act: 5.1470. Min Act: -0.1700
Data Index: 4372917 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5220. Min Range: -5.5220
Max Act: 5.1470. Min Act: -0.1700
Data Index: 865690 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5220. Min Range: -5.5220
Max Act: 5.1470. Min Act: -0.1700
Data Index: 1061955 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5220. Min Range: -5.5220
Max Act: 5.1158. Min Act: -0.1700
Data Index: 1261148 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5220. Min Range: -5.5220
Max Act: 5.1158. Min Act: -0.1700
Data Index: 4989977 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5220. Min Range: -5.5220
Max Act: 5.0845. Min Act: -0.1700
Data Index: 7477055 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5220. Min Range: -5.5220
Max Act: 5.0845. Min Act: -0.1700
Data Index: 6842146 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5220. Min Range: -5.5220
Max Act: 5.0845. Min Act: -0.1700
Data Index: 3923731 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5220. Min Range: -5.5220
Max Act: 5.0845. Min Act: -0.1700
Data Index: 3752628 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19