Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 632 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6545. Min Range: -5.6545
Max Act: 5.6545. Min Act: -0.1700
Data Index: 3692203 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6545. Min Range: -5.6545
Max Act: 5.4045. Min Act: -0.1700
Data Index: 7414006 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6545. Min Range: -5.6545
Max Act: 5.3420. Min Act: -0.1700
Data Index: 4310769 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6545. Min Range: -5.6545
Max Act: 5.3107. Min Act: -0.1700
Data Index: 8586654 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6545. Min Range: -5.6545
Max Act: 5.2795. Min Act: -0.1700
Data Index: 81078 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6545. Min Range: -5.6545
Max Act: 5.2170. Min Act: -0.1700
Data Index: 6555826 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6545. Min Range: -5.6545
Max Act: 5.2482. Min Act: -0.1700
Data Index: 2326155 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6545. Min Range: -5.6545
Max Act: 5.2170. Min Act: -0.1700
Data Index: 753801 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6545. Min Range: -5.6545
Max Act: 5.2170. Min Act: -0.1700
Data Index: 781783 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6545. Min Range: -5.6545
Max Act: 5.2170. Min Act: -0.1700
Data Index: 4395998 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6545. Min Range: -5.6545
Max Act: 5.2170. Min Act: -0.1700
Data Index: 4420897 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6545. Min Range: -5.6545
Max Act: 5.2482. Min Act: -0.1700
Data Index: 4911909 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6545. Min Range: -5.6545
Max Act: 5.1857. Min Act: -0.1700
Data Index: 2481749 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6545. Min Range: -5.6545
Max Act: 5.1857. Min Act: -0.1700
Data Index: 3855509 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6545. Min Range: -5.6545
Max Act: 5.1857. Min Act: -0.1700
Data Index: 3665421 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6545. Min Range: -5.6545
Max Act: 5.1232. Min Act: -0.1700
Data Index: 224510 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6545. Min Range: -5.6545
Max Act: 5.1232. Min Act: -0.1700
Data Index: 194644 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6545. Min Range: -5.6545
Max Act: 5.1232. Min Act: -0.1700
Data Index: 8161710 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6545. Min Range: -5.6545
Max Act: 5.1232. Min Act: -0.1700
Data Index: 6382340 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6545. Min Range: -5.6545
Max Act: 5.0920. Min Act: -0.1700
Data Index: 254844 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19