Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4054 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0243. Min Range: -2.0243
Max Act: 2.0243. Min Act: -0.1700
Data Index: 7977780 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0243. Min Range: -2.0243
Max Act: 2.0074. Min Act: -0.1697
Data Index: 3492702 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0243. Min Range: -2.0243
Max Act: 1.9905. Min Act: -0.1700
Data Index: 5420645 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0243. Min Range: -2.0243
Max Act: 1.9736. Min Act: -0.1700
Data Index: 1064627 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0243. Min Range: -2.0243
Max Act: 1.8886. Min Act: -0.1700
Data Index: 5848526 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0243. Min Range: -2.0243
Max Act: 1.8886. Min Act: -0.1700
Data Index: 350033 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0243. Min Range: -2.0243
Max Act: 1.8800. Min Act: -0.1700
Data Index: 240639 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0243. Min Range: -2.0243
Max Act: 1.8544. Min Act: -0.1697
Data Index: 5243434 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0243. Min Range: -2.0243
Max Act: 1.8544. Min Act: -0.1700
Data Index: 6063065 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0243. Min Range: -2.0243
Max Act: 1.8115. Min Act: -0.1700
Data Index: 3717583 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0243. Min Range: -2.0243
Max Act: 1.8287. Min Act: -0.1700
Data Index: 2663493 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0243. Min Range: -2.0243
Max Act: 1.8287. Min Act: -0.1700
Data Index: 2917752 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0243. Min Range: -2.0243
Max Act: 1.8287. Min Act: -0.1700
Data Index: 6056146 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0243. Min Range: -2.0243
Max Act: 1.8115. Min Act: -0.1700
Data Index: 6516410 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0243. Min Range: -2.0243
Max Act: 1.8115. Min Act: -0.1700
Data Index: 6554557 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0243. Min Range: -2.0243
Max Act: 1.8201. Min Act: -0.1700
Data Index: 5162147 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0243. Min Range: -2.0243
Max Act: 1.8201. Min Act: -0.1700
Data Index: 1955072 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0243. Min Range: -2.0243
Max Act: 1.7943. Min Act: -0.1700
Data Index: 2666031 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0243. Min Range: -2.0243
Max Act: 1.8115. Min Act: -0.1700
Data Index: 3221472 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0243. Min Range: -2.0243
Max Act: 1.8029. Min Act: -0.1700
Data Index: 3783391 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19