Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2415 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.3691. Min Range: -8.3691
Max Act: 8.3691. Min Act: -0.1700
Data Index: 241898 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3691. Min Range: -8.3691
Max Act: 8.3379. Min Act: -0.1700
Data Index: 2800959 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3691. Min Range: -8.3691
Max Act: 8.0566. Min Act: -0.1700
Data Index: 7288162 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3691. Min Range: -8.3691
Max Act: 8.0566. Min Act: -0.1700
Data Index: 1149063 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3691. Min Range: -8.3691
Max Act: 8.1191. Min Act: -0.1700
Data Index: 6354623 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3691. Min Range: -8.3691
Max Act: 7.9941. Min Act: -0.1700
Data Index: 3416181 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3691. Min Range: -8.3691
Max Act: 8.0254. Min Act: -0.1700
Data Index: 2588367 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3691. Min Range: -8.3691
Max Act: 7.9941. Min Act: -0.1700
Data Index: 8295703 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3691. Min Range: -8.3691
Max Act: 7.9941. Min Act: -0.1700
Data Index: 8073570 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3691. Min Range: -8.3691
Max Act: 7.9316. Min Act: -0.1700
Data Index: 8257448 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3691. Min Range: -8.3691
Max Act: 7.9316. Min Act: -0.1700
Data Index: 2481479 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3691. Min Range: -8.3691
Max Act: 7.8691. Min Act: -0.1700
Data Index: 981624 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3691. Min Range: -8.3691
Max Act: 7.8379. Min Act: -0.1700
Data Index: 8057519 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3691. Min Range: -8.3691
Max Act: 7.9004. Min Act: -0.1700
Data Index: 3278575 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3691. Min Range: -8.3691
Max Act: 7.8066. Min Act: -0.1700
Data Index: 6715384 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3691. Min Range: -8.3691
Max Act: 7.9004. Min Act: -0.1700
Data Index: 753349 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3691. Min Range: -8.3691
Max Act: 7.8066. Min Act: -0.1700
Data Index: 8224894 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3691. Min Range: -8.3691
Max Act: 7.8066. Min Act: -0.1700
Data Index: 3566809 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3691. Min Range: -8.3691
Max Act: 7.6816. Min Act: -0.1700
Data Index: 2146214 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3691. Min Range: -8.3691
Max Act: 7.7129. Min Act: -0.1700
Data Index: 4624262 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19