Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2774 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4350. Min Range: -7.4350
Max Act: 7.4350. Min Act: -0.1700
Data Index: 6786521 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4350. Min Range: -7.4350
Max Act: 7.2163. Min Act: -0.1700
Data Index: 220491 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4350. Min Range: -7.4350
Max Act: 7.1225. Min Act: -0.1700
Data Index: 59115 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4350. Min Range: -7.4350
Max Act: 7.1225. Min Act: -0.1700
Data Index: 3477651 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4350. Min Range: -7.4350
Max Act: 7.0913. Min Act: -0.1700
Data Index: 6911003 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4350. Min Range: -7.4350
Max Act: 7.0600. Min Act: -0.1700
Data Index: 5934051 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4350. Min Range: -7.4350
Max Act: 6.9975. Min Act: -0.1700
Data Index: 7306207 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4350. Min Range: -7.4350
Max Act: 6.9975. Min Act: -0.1700
Data Index: 1828617 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4350. Min Range: -7.4350
Max Act: 6.9663. Min Act: -0.1700
Data Index: 4141238 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4350. Min Range: -7.4350
Max Act: 6.9663. Min Act: -0.1700
Data Index: 6558276 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4350. Min Range: -7.4350
Max Act: 6.9663. Min Act: -0.1700
Data Index: 1431564 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4350. Min Range: -7.4350
Max Act: 6.9350. Min Act: -0.1700
Data Index: 6165466 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4350. Min Range: -7.4350
Max Act: 6.9038. Min Act: -0.1700
Data Index: 7458321 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4350. Min Range: -7.4350
Max Act: 6.8725. Min Act: -0.1700
Data Index: 3916261 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4350. Min Range: -7.4350
Max Act: 6.8725. Min Act: -0.1700
Data Index: 7994892 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4350. Min Range: -7.4350
Max Act: 6.8725. Min Act: -0.1700
Data Index: 1220852 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4350. Min Range: -7.4350
Max Act: 6.8413. Min Act: -0.1700
Data Index: 4420033 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4350. Min Range: -7.4350
Max Act: 6.8413. Min Act: -0.1700
Data Index: 2262254 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4350. Min Range: -7.4350
Max Act: 6.8413. Min Act: -0.1700
Data Index: 7877552 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4350. Min Range: -7.4350
Max Act: 6.8100. Min Act: -0.1700
Data Index: 6133203 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19