Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5872 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4568. Min Range: -7.4568
Max Act: 7.4568. Min Act: -0.1700
Data Index: 4840423 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4568. Min Range: -7.4568
Max Act: 7.2693. Min Act: -0.1700
Data Index: 959241 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4568. Min Range: -7.4568
Max Act: 7.2693. Min Act: -0.1700
Data Index: 2396284 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4568. Min Range: -7.4568
Max Act: 7.2693. Min Act: -0.1700
Data Index: 5447312 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4568. Min Range: -7.4568
Max Act: 7.2068. Min Act: -0.1700
Data Index: 5375528 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4568. Min Range: -7.4568
Max Act: 7.1755. Min Act: -0.1700
Data Index: 2560901 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4568. Min Range: -7.4568
Max Act: 7.1443. Min Act: -0.1700
Data Index: 5627053 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4568. Min Range: -7.4568
Max Act: 7.1443. Min Act: -0.1700
Data Index: 1028503 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4568. Min Range: -7.4568
Max Act: 7.1443. Min Act: -0.1700
Data Index: 1233831 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4568. Min Range: -7.4568
Max Act: 7.1130. Min Act: -0.1700
Data Index: 141406 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4568. Min Range: -7.4568
Max Act: 7.1130. Min Act: -0.1700
Data Index: 218146 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4568. Min Range: -7.4568
Max Act: 7.1130. Min Act: -0.1700
Data Index: 121640 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4568. Min Range: -7.4568
Max Act: 7.1130. Min Act: -0.1700
Data Index: 3141163 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4568. Min Range: -7.4568
Max Act: 7.0818. Min Act: -0.1700
Data Index: 8152171 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4568. Min Range: -7.4568
Max Act: 7.0818. Min Act: -0.1700
Data Index: 6739746 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4568. Min Range: -7.4568
Max Act: 7.0818. Min Act: -0.1700
Data Index: 1920793 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4568. Min Range: -7.4568
Max Act: 7.0505. Min Act: -0.1700
Data Index: 5457841 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4568. Min Range: -7.4568
Max Act: 7.0193. Min Act: -0.1700
Data Index: 4522001 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4568. Min Range: -7.4568
Max Act: 7.0505. Min Act: -0.1700
Data Index: 319714 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4568. Min Range: -7.4568
Max Act: 7.0505. Min Act: -0.1700
Data Index: 1850079 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #19