Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4585 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4000. Min Range: -3.4000
Max Act: 3.4000. Min Act: -0.1700
Data Index: 3395043 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4000. Min Range: -3.4000
Max Act: 3.3372. Min Act: -0.1700
Data Index: 1540085 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4000. Min Range: -3.4000
Max Act: 3.3059. Min Act: -0.1700
Data Index: 7070147 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4000. Min Range: -3.4000
Max Act: 3.3216. Min Act: -0.1700
Data Index: 4689077 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4000. Min Range: -3.4000
Max Act: 3.3059. Min Act: -0.1700
Data Index: 2477815 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4000. Min Range: -3.4000
Max Act: 3.2902. Min Act: -0.1700
Data Index: 6494985 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4000. Min Range: -3.4000
Max Act: 3.2902. Min Act: -0.1700
Data Index: 5475860 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4000. Min Range: -3.4000
Max Act: 3.2430. Min Act: -0.1700
Data Index: 1552988 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4000. Min Range: -3.4000
Max Act: 3.2588. Min Act: -0.1700
Data Index: 2785085 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4000. Min Range: -3.4000
Max Act: 3.2273. Min Act: -0.1700
Data Index: 7072333 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4000. Min Range: -3.4000
Max Act: 3.2273. Min Act: -0.1700
Data Index: 6117820 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4000. Min Range: -3.4000
Max Act: 3.2273. Min Act: -0.1700
Data Index: 5292540 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4000. Min Range: -3.4000
Max Act: 3.2116. Min Act: -0.1700
Data Index: 6145911 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4000. Min Range: -3.4000
Max Act: 3.2116. Min Act: -0.1700
Data Index: 1503888 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4000. Min Range: -3.4000
Max Act: 3.1959. Min Act: -0.1700
Data Index: 8181441 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4000. Min Range: -3.4000
Max Act: 3.1959. Min Act: -0.1700
Data Index: 6000963 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4000. Min Range: -3.4000
Max Act: 3.1959. Min Act: -0.1700
Data Index: 3945816 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4000. Min Range: -3.4000
Max Act: 3.1801. Min Act: -0.1700
Data Index: 1696933 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4000. Min Range: -3.4000
Max Act: 3.1959. Min Act: -0.1700
Data Index: 1962384 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4000. Min Range: -3.4000
Max Act: 3.1644. Min Act: -0.1700
Data Index: 7614028 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19