Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3933 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1279. Min Range: -5.1279
Max Act: 5.1279. Min Act: -0.1700
Data Index: 1721934 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1279. Min Range: -5.1279
Max Act: 5.0029. Min Act: -0.1700
Data Index: 7132581 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1279. Min Range: -5.1279
Max Act: 4.9092. Min Act: -0.1700
Data Index: 3667441 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1279. Min Range: -5.1279
Max Act: 4.8154. Min Act: -0.1700
Data Index: 3562175 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1279. Min Range: -5.1279
Max Act: 4.7217. Min Act: -0.1700
Data Index: 3718032 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1279. Min Range: -5.1279
Max Act: 4.7217. Min Act: -0.1700
Data Index: 7017293 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1279. Min Range: -5.1279
Max Act: 4.6904. Min Act: -0.1700
Data Index: 5191417 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1279. Min Range: -5.1279
Max Act: 4.6904. Min Act: -0.1700
Data Index: 1681598 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1279. Min Range: -5.1279
Max Act: 4.6904. Min Act: -0.1700
Data Index: 8041794 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1279. Min Range: -5.1279
Max Act: 4.6904. Min Act: -0.1700
Data Index: 1002910 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1279. Min Range: -5.1279
Max Act: 4.6592. Min Act: -0.1700
Data Index: 6472644 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1279. Min Range: -5.1279
Max Act: 4.5967. Min Act: -0.1700
Data Index: 3041034 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1279. Min Range: -5.1279
Max Act: 4.5654. Min Act: -0.1700
Data Index: 3628555 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1279. Min Range: -5.1279
Max Act: 4.5654. Min Act: -0.1700
Data Index: 8008822 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1279. Min Range: -5.1279
Max Act: 4.5654. Min Act: -0.1700
Data Index: 5392732 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1279. Min Range: -5.1279
Max Act: 4.5967. Min Act: -0.1700
Data Index: 8004246 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1279. Min Range: -5.1279
Max Act: 4.5654. Min Act: -0.1700
Data Index: 1974018 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1279. Min Range: -5.1279
Max Act: 4.5654. Min Act: -0.1700
Data Index: 8455842 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1279. Min Range: -5.1279
Max Act: 4.5967. Min Act: -0.1700
Data Index: 8041795 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1279. Min Range: -5.1279
Max Act: 4.5342. Min Act: -0.1700
Data Index: 1333881 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19