Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5081 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4532. Min Range: -6.4532
Max Act: 6.4220. Min Act: -0.1700
Data Index: 2231663 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4532. Min Range: -6.4532
Max Act: 6.4532. Min Act: -0.1700
Data Index: 5025998 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4532. Min Range: -6.4532
Max Act: 6.4220. Min Act: -0.1700
Data Index: 7218059 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4532. Min Range: -6.4532
Max Act: 6.3907. Min Act: -0.1700
Data Index: 7218069 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4532. Min Range: -6.4532
Max Act: 6.3595. Min Act: -0.1700
Data Index: 7130487 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4532. Min Range: -6.4532
Max Act: 6.3595. Min Act: -0.1700
Data Index: 568035 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4532. Min Range: -6.4532
Max Act: 6.2970. Min Act: -0.1700
Data Index: 287561 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4532. Min Range: -6.4532
Max Act: 6.2657. Min Act: -0.1700
Data Index: 1369830 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4532. Min Range: -6.4532
Max Act: 6.2032. Min Act: -0.1700
Data Index: 2991716 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4532. Min Range: -6.4532
Max Act: 6.2032. Min Act: -0.1700
Data Index: 1963810 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4532. Min Range: -6.4532
Max Act: 6.2032. Min Act: -0.1700
Data Index: 4220041 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4532. Min Range: -6.4532
Max Act: 6.1720. Min Act: -0.1700
Data Index: 5459689 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4532. Min Range: -6.4532
Max Act: 6.2345. Min Act: -0.1700
Data Index: 7139352 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4532. Min Range: -6.4532
Max Act: 6.1720. Min Act: -0.1700
Data Index: 6814774 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4532. Min Range: -6.4532
Max Act: 6.1720. Min Act: -0.1700
Data Index: 6304813 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4532. Min Range: -6.4532
Max Act: 6.1095. Min Act: -0.1700
Data Index: 2564874 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4532. Min Range: -6.4532
Max Act: 6.1407. Min Act: -0.1700
Data Index: 7408536 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4532. Min Range: -6.4532
Max Act: 6.1407. Min Act: -0.1700
Data Index: 8210143 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4532. Min Range: -6.4532
Max Act: 6.1407. Min Act: -0.1700
Data Index: 4152930 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4532. Min Range: -6.4532
Max Act: 6.1095. Min Act: -0.1700
Data Index: 1553144 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19