Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3921 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8845. Min Range: -5.8845
Max Act: 5.8845. Min Act: -0.1700
Data Index: 4725602 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8845. Min Range: -5.8845
Max Act: 5.8845. Min Act: -0.1700
Data Index: 4837828 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8845. Min Range: -5.8845
Max Act: 5.7907. Min Act: -0.1700
Data Index: 6016756 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8845. Min Range: -5.8845
Max Act: 5.7282. Min Act: -0.1700
Data Index: 6570835 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8845. Min Range: -5.8845
Max Act: 5.6970. Min Act: -0.1700
Data Index: 5101263 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8845. Min Range: -5.8845
Max Act: 5.5720. Min Act: -0.1700
Data Index: 6975781 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8845. Min Range: -5.8845
Max Act: 5.5407. Min Act: -0.1700
Data Index: 7272290 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8845. Min Range: -5.8845
Max Act: 5.5407. Min Act: -0.1700
Data Index: 7144613 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8845. Min Range: -5.8845
Max Act: 5.5720. Min Act: -0.1700
Data Index: 8277788 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8845. Min Range: -5.8845
Max Act: 5.5095. Min Act: -0.1700
Data Index: 3103329 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8845. Min Range: -5.8845
Max Act: 5.5095. Min Act: -0.1700
Data Index: 4268359 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8845. Min Range: -5.8845
Max Act: 5.5095. Min Act: -0.1700
Data Index: 72019 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8845. Min Range: -5.8845
Max Act: 5.5095. Min Act: -0.1700
Data Index: 6383198 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8845. Min Range: -5.8845
Max Act: 5.5095. Min Act: -0.1700
Data Index: 375670 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8845. Min Range: -5.8845
Max Act: 5.4782. Min Act: -0.1700
Data Index: 4933750 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8845. Min Range: -5.8845
Max Act: 5.4470. Min Act: -0.1700
Data Index: 8502900 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8845. Min Range: -5.8845
Max Act: 5.4470. Min Act: -0.1700
Data Index: 213222 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8845. Min Range: -5.8845
Max Act: 5.4470. Min Act: -0.1700
Data Index: 8145787 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8845. Min Range: -5.8845
Max Act: 5.4157. Min Act: -0.1700
Data Index: 3949618 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8845. Min Range: -5.8845
Max Act: 5.4157. Min Act: -0.1700
Data Index: 5562806 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19