Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2680 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4816. Min Range: -8.4816
Max Act: 8.4816. Min Act: -0.1700
Data Index: 4064477 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4816. Min Range: -8.4816
Max Act: 8.3566. Min Act: -0.1700
Data Index: 4064486 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4816. Min Range: -8.4816
Max Act: 8.1378. Min Act: -0.1700
Data Index: 2492712 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4816. Min Range: -8.4816
Max Act: 8.0128. Min Act: -0.1700
Data Index: 949843 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4816. Min Range: -8.4816
Max Act: 7.9503. Min Act: -0.1700
Data Index: 5572198 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4816. Min Range: -8.4816
Max Act: 7.9503. Min Act: -0.1700
Data Index: 8056773 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4816. Min Range: -8.4816
Max Act: 7.8878. Min Act: -0.1700
Data Index: 4631112 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4816. Min Range: -8.4816
Max Act: 7.8878. Min Act: -0.1700
Data Index: 764426 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4816. Min Range: -8.4816
Max Act: 7.8878. Min Act: -0.1700
Data Index: 7582055 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4816. Min Range: -8.4816
Max Act: 7.8253. Min Act: -0.1700
Data Index: 937117 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4816. Min Range: -8.4816
Max Act: 7.8566. Min Act: -0.1700
Data Index: 7609852 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4816. Min Range: -8.4816
Max Act: 7.8566. Min Act: -0.1700
Data Index: 4064469 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4816. Min Range: -8.4816
Max Act: 7.8878. Min Act: -0.1700
Data Index: 4594235 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4816. Min Range: -8.4816
Max Act: 7.7628. Min Act: -0.1700
Data Index: 1869696 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4816. Min Range: -8.4816
Max Act: 7.7628. Min Act: -0.1700
Data Index: 382623 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4816. Min Range: -8.4816
Max Act: 7.7316. Min Act: -0.1700
Data Index: 4815297 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4816. Min Range: -8.4816
Max Act: 7.7628. Min Act: -0.1700
Data Index: 4379128 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4816. Min Range: -8.4816
Max Act: 7.7628. Min Act: -0.1700
Data Index: 7609872 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4816. Min Range: -8.4816
Max Act: 7.7316. Min Act: -0.1700
Data Index: 5825457 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4816. Min Range: -8.4816
Max Act: 7.6378. Min Act: -0.1700
Data Index: 312495 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19