Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1165 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3787. Min Range: -2.3787
Max Act: 2.3787. Min Act: -0.1700
Data Index: 8113209 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3787. Min Range: -2.3787
Max Act: 2.2306. Min Act: -0.1700
Data Index: 360210 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3787. Min Range: -2.3787
Max Act: 2.2637. Min Act: -0.1700
Data Index: 4542662 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3787. Min Range: -2.3787
Max Act: 2.2472. Min Act: -0.1700
Data Index: 5606419 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3787. Min Range: -2.3787
Max Act: 2.2306. Min Act: -0.1699
Data Index: 1265201 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3787. Min Range: -2.3787
Max Act: 2.2141. Min Act: -0.1700
Data Index: 5057364 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3787. Min Range: -2.3787
Max Act: 2.1975. Min Act: -0.1700
Data Index: 8063318 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3787. Min Range: -2.3787
Max Act: 2.1975. Min Act: -0.1700
Data Index: 2342228 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3787. Min Range: -2.3787
Max Act: 2.1643. Min Act: -0.1700
Data Index: 7684603 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3787. Min Range: -2.3787
Max Act: 2.1809. Min Act: -0.1700
Data Index: 3144059 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3787. Min Range: -2.3787
Max Act: 2.1809. Min Act: -0.1700
Data Index: 7862984 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3787. Min Range: -2.3787
Max Act: 2.1809. Min Act: -0.1700
Data Index: 4246019 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3787. Min Range: -2.3787
Max Act: 2.1809. Min Act: -0.1700
Data Index: 6292165 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3787. Min Range: -2.3787
Max Act: 2.1643. Min Act: -0.1700
Data Index: 5653233 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3787. Min Range: -2.3787
Max Act: 2.1476. Min Act: -0.1700
Data Index: 3336950 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3787. Min Range: -2.3787
Max Act: 2.1309. Min Act: -0.1700
Data Index: 3844587 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3787. Min Range: -2.3787
Max Act: 2.1476. Min Act: -0.1700
Data Index: 2742613 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3787. Min Range: -2.3787
Max Act: 2.1476. Min Act: -0.1700
Data Index: 360209 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3787. Min Range: -2.3787
Max Act: 2.1476. Min Act: -0.1700
Data Index: 7302573 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3787. Min Range: -2.3787
Max Act: 2.1309. Min Act: -0.1700
Data Index: 3961293 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #19