Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1854 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8660. Min Range: -4.8660
Max Act: 4.8660. Min Act: -0.1700
Data Index: 6260850 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8660. Min Range: -4.8660
Max Act: 4.8035. Min Act: -0.1700
Data Index: 4027250 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8660. Min Range: -4.8660
Max Act: 4.8035. Min Act: -0.1700
Data Index: 2694846 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8660. Min Range: -4.8660
Max Act: 4.7723. Min Act: -0.1700
Data Index: 54136 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8660. Min Range: -4.8660
Max Act: 4.7410. Min Act: -0.1700
Data Index: 6445502 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8660. Min Range: -4.8660
Max Act: 4.7098. Min Act: -0.1700
Data Index: 3368477 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8660. Min Range: -4.8660
Max Act: 4.7098. Min Act: -0.1700
Data Index: 5349370 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8660. Min Range: -4.8660
Max Act: 4.6785. Min Act: -0.1700
Data Index: 7668519 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8660. Min Range: -4.8660
Max Act: 4.6785. Min Act: -0.1700
Data Index: 1090288 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8660. Min Range: -4.8660
Max Act: 4.6785. Min Act: -0.1700
Data Index: 6497937 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8660. Min Range: -4.8660
Max Act: 4.6785. Min Act: -0.1700
Data Index: 3735859 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8660. Min Range: -4.8660
Max Act: 4.6785. Min Act: -0.1700
Data Index: 7711791 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8660. Min Range: -4.8660
Max Act: 4.5848. Min Act: -0.1700
Data Index: 774337 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8660. Min Range: -4.8660
Max Act: 4.6160. Min Act: -0.1700
Data Index: 1818207 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8660. Min Range: -4.8660
Max Act: 4.6160. Min Act: -0.1700
Data Index: 5476983 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8660. Min Range: -4.8660
Max Act: 4.6160. Min Act: -0.1700
Data Index: 2850874 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8660. Min Range: -4.8660
Max Act: 4.6160. Min Act: -0.1700
Data Index: 4833619 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8660. Min Range: -4.8660
Max Act: 4.6160. Min Act: -0.1700
Data Index: 7035583 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8660. Min Range: -4.8660
Max Act: 4.6160. Min Act: -0.1700
Data Index: 2360189 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8660. Min Range: -4.8660
Max Act: 4.5848. Min Act: -0.1700
Data Index: 357240 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19