Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1312 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9172. Min Range: -6.9172
Max Act: 6.9172. Min Act: -0.1700
Data Index: 3868236 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9172. Min Range: -6.9172
Max Act: 6.6047. Min Act: -0.1700
Data Index: 7871222 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9172. Min Range: -6.9172
Max Act: 6.4485. Min Act: -0.1700
Data Index: 2757817 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9172. Min Range: -6.9172
Max Act: 6.3860. Min Act: -0.1700
Data Index: 245010 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9172. Min Range: -6.9172
Max Act: 6.2922. Min Act: -0.1700
Data Index: 2860727 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9172. Min Range: -6.9172
Max Act: 6.2610. Min Act: -0.1700
Data Index: 7917719 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9172. Min Range: -6.9172
Max Act: 6.2610. Min Act: -0.1700
Data Index: 3562216 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9172. Min Range: -6.9172
Max Act: 6.1985. Min Act: -0.1700
Data Index: 7990447 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9172. Min Range: -6.9172
Max Act: 6.1985. Min Act: -0.1700
Data Index: 1585651 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9172. Min Range: -6.9172
Max Act: 6.1047. Min Act: -0.1700
Data Index: 7339604 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9172. Min Range: -6.9172
Max Act: 6.1047. Min Act: -0.1700
Data Index: 7767849 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9172. Min Range: -6.9172
Max Act: 6.1047. Min Act: -0.1700
Data Index: 5190560 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9172. Min Range: -6.9172
Max Act: 6.0735. Min Act: -0.1700
Data Index: 7267680 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9172. Min Range: -6.9172
Max Act: 6.0735. Min Act: -0.1700
Data Index: 8468944 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9172. Min Range: -6.9172
Max Act: 6.0110. Min Act: -0.1700
Data Index: 4566015 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9172. Min Range: -6.9172
Max Act: 6.0422. Min Act: -0.1700
Data Index: 3175848 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9172. Min Range: -6.9172
Max Act: 6.0422. Min Act: -0.1700
Data Index: 492014 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9172. Min Range: -6.9172
Max Act: 6.0110. Min Act: -0.1700
Data Index: 251042 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9172. Min Range: -6.9172
Max Act: 6.0110. Min Act: -0.1700
Data Index: 202961 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9172. Min Range: -6.9172
Max Act: 6.0422. Min Act: -0.1700
Data Index: 4913343 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19