Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 534 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4987. Min Range: -4.4987
Max Act: 4.4987. Min Act: -0.1700
Data Index: 5015925 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4987. Min Range: -4.4987
Max Act: 4.4675. Min Act: -0.1700
Data Index: 6296330 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4987. Min Range: -4.4987
Max Act: 4.4050. Min Act: -0.1700
Data Index: 8673131 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4987. Min Range: -4.4987
Max Act: 4.3737. Min Act: -0.1700
Data Index: 4652303 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4987. Min Range: -4.4987
Max Act: 4.4050. Min Act: -0.1700
Data Index: 977380 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4987. Min Range: -4.4987
Max Act: 4.3425. Min Act: -0.1700
Data Index: 2034165 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4987. Min Range: -4.4987
Max Act: 4.3737. Min Act: -0.1700
Data Index: 4714892 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4987. Min Range: -4.4987
Max Act: 4.3737. Min Act: -0.1700
Data Index: 8767601 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4987. Min Range: -4.4987
Max Act: 4.3425. Min Act: -0.1700
Data Index: 2976859 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4987. Min Range: -4.4987
Max Act: 4.3112. Min Act: -0.1700
Data Index: 1943358 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4987. Min Range: -4.4987
Max Act: 4.3112. Min Act: -0.1700
Data Index: 180264 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4987. Min Range: -4.4987
Max Act: 4.3425. Min Act: -0.1700
Data Index: 7307755 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4987. Min Range: -4.4987
Max Act: 4.3112. Min Act: -0.1700
Data Index: 5026360 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4987. Min Range: -4.4987
Max Act: 4.3425. Min Act: -0.1700
Data Index: 3314415 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4987. Min Range: -4.4987
Max Act: 4.2800. Min Act: -0.1700
Data Index: 6748049 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4987. Min Range: -4.4987
Max Act: 4.3112. Min Act: -0.1700
Data Index: 7939273 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4987. Min Range: -4.4987
Max Act: 4.2800. Min Act: -0.1700
Data Index: 5582959 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4987. Min Range: -4.4987
Max Act: 4.2800. Min Act: -0.1700
Data Index: 4249237 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4987. Min Range: -4.4987
Max Act: 4.2800. Min Act: -0.1700
Data Index: 7500971 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4987. Min Range: -4.4987
Max Act: 4.2800. Min Act: -0.1700
Data Index: 4282478 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19