Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2694 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9109. Min Range: -4.9109
Max Act: 4.9109. Min Act: -0.1700
Data Index: 1584664 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9109. Min Range: -4.9109
Max Act: 4.8172. Min Act: -0.1700
Data Index: 8781950 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9109. Min Range: -4.9109
Max Act: 4.8797. Min Act: -0.1700
Data Index: 757045 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9109. Min Range: -4.9109
Max Act: 4.8172. Min Act: -0.1700
Data Index: 977067 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9109. Min Range: -4.9109
Max Act: 4.7547. Min Act: -0.1700
Data Index: 3349109 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9109. Min Range: -4.9109
Max Act: 4.7859. Min Act: -0.1700
Data Index: 1558971 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9109. Min Range: -4.9109
Max Act: 4.7234. Min Act: -0.1700
Data Index: 6660648 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9109. Min Range: -4.9109
Max Act: 4.6922. Min Act: -0.1700
Data Index: 3557626 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9109. Min Range: -4.9109
Max Act: 4.7234. Min Act: -0.1700
Data Index: 6680711 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9109. Min Range: -4.9109
Max Act: 4.6922. Min Act: -0.1700
Data Index: 6707077 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9109. Min Range: -4.9109
Max Act: 4.6609. Min Act: -0.1700
Data Index: 4995685 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9109. Min Range: -4.9109
Max Act: 4.6609. Min Act: -0.1700
Data Index: 1222371 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9109. Min Range: -4.9109
Max Act: 4.6609. Min Act: -0.1700
Data Index: 7512538 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9109. Min Range: -4.9109
Max Act: 4.6297. Min Act: -0.1700
Data Index: 5605650 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9109. Min Range: -4.9109
Max Act: 4.6297. Min Act: -0.1700
Data Index: 8563496 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9109. Min Range: -4.9109
Max Act: 4.5672. Min Act: -0.1700
Data Index: 6291757 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9109. Min Range: -4.9109
Max Act: 4.5984. Min Act: -0.1700
Data Index: 5828231 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9109. Min Range: -4.9109
Max Act: 4.6297. Min Act: -0.1700
Data Index: 3186797 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9109. Min Range: -4.9109
Max Act: 4.5984. Min Act: -0.1700
Data Index: 7232558 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9109. Min Range: -4.9109
Max Act: 4.6922. Min Act: -0.1700
Data Index: 609145 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19