Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2837 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0765. Min Range: -7.0765
Max Act: 7.0765. Min Act: -0.1700
Data Index: 2928606 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0765. Min Range: -7.0765
Max Act: 6.7640. Min Act: -0.1700
Data Index: 2985136 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0765. Min Range: -7.0765
Max Act: 6.7015. Min Act: -0.1700
Data Index: 8195118 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0765. Min Range: -7.0765
Max Act: 6.7328. Min Act: -0.1700
Data Index: 2072071 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0765. Min Range: -7.0765
Max Act: 6.7640. Min Act: -0.1700
Data Index: 1926219 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0765. Min Range: -7.0765
Max Act: 6.6078. Min Act: -0.1700
Data Index: 5555842 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0765. Min Range: -7.0765
Max Act: 6.4828. Min Act: -0.1700
Data Index: 1770100 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0765. Min Range: -7.0765
Max Act: 6.4515. Min Act: -0.1700
Data Index: 3942573 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0765. Min Range: -7.0765
Max Act: 6.4203. Min Act: -0.1700
Data Index: 5802532 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0765. Min Range: -7.0765
Max Act: 6.3890. Min Act: -0.1700
Data Index: 6321875 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0765. Min Range: -7.0765
Max Act: 6.3578. Min Act: -0.1700
Data Index: 7470294 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0765. Min Range: -7.0765
Max Act: 6.2953. Min Act: -0.1700
Data Index: 5555845 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0765. Min Range: -7.0765
Max Act: 6.2953. Min Act: -0.1700
Data Index: 1770094 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0765. Min Range: -7.0765
Max Act: 6.2640. Min Act: -0.1700
Data Index: 3094959 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0765. Min Range: -7.0765
Max Act: 6.1703. Min Act: -0.1700
Data Index: 323619 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0765. Min Range: -7.0765
Max Act: 6.2953. Min Act: -0.1700
Data Index: 1165435 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0765. Min Range: -7.0765
Max Act: 6.1703. Min Act: -0.1700
Data Index: 368498 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0765. Min Range: -7.0765
Max Act: 6.1703. Min Act: -0.1700
Data Index: 5111059 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0765. Min Range: -7.0765
Max Act: 6.2015. Min Act: -0.1700
Data Index: 4317607 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0765. Min Range: -7.0765
Max Act: 6.2640. Min Act: -0.1700
Data Index: 6987168 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19