Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1663 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7744. Min Range: -6.7744
Max Act: 6.7744. Min Act: -0.1700
Data Index: 187257 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7744. Min Range: -6.7744
Max Act: 6.7432. Min Act: -0.1700
Data Index: 2009530 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7744. Min Range: -6.7744
Max Act: 6.7744. Min Act: -0.1700
Data Index: 8325494 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7744. Min Range: -6.7744
Max Act: 6.7119. Min Act: -0.1700
Data Index: 4627219 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7744. Min Range: -6.7744
Max Act: 6.7119. Min Act: -0.1700
Data Index: 2604057 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7744. Min Range: -6.7744
Max Act: 6.6494. Min Act: -0.1700
Data Index: 531069 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7744. Min Range: -6.7744
Max Act: 6.5869. Min Act: -0.1700
Data Index: 6926829 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7744. Min Range: -6.7744
Max Act: 6.5557. Min Act: -0.1700
Data Index: 7346288 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7744. Min Range: -6.7744
Max Act: 6.5869. Min Act: -0.1700
Data Index: 4298853 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7744. Min Range: -6.7744
Max Act: 6.5244. Min Act: -0.1700
Data Index: 6497316 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7744. Min Range: -6.7744
Max Act: 6.5244. Min Act: -0.1700
Data Index: 4529415 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7744. Min Range: -6.7744
Max Act: 6.4619. Min Act: -0.1700
Data Index: 155232 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7744. Min Range: -6.7744
Max Act: 6.4932. Min Act: -0.1700
Data Index: 4078834 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7744. Min Range: -6.7744
Max Act: 6.5244. Min Act: -0.1700
Data Index: 804222 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7744. Min Range: -6.7744
Max Act: 6.4932. Min Act: -0.1700
Data Index: 1411359 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7744. Min Range: -6.7744
Max Act: 6.5244. Min Act: -0.1700
Data Index: 6406960 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7744. Min Range: -6.7744
Max Act: 6.4932. Min Act: -0.1700
Data Index: 8283595 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7744. Min Range: -6.7744
Max Act: 6.4932. Min Act: -0.1700
Data Index: 3791356 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7744. Min Range: -6.7744
Max Act: 6.4932. Min Act: -0.1700
Data Index: 5162368 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7744. Min Range: -6.7744
Max Act: 6.4619. Min Act: -0.1700
Data Index: 3998225 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #19