Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2287 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5355. Min Range: -4.5355
Max Act: 4.5355. Min Act: -0.1700
Data Index: 6699448 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5355. Min Range: -4.5355
Max Act: 4.4730. Min Act: -0.1700
Data Index: 2496188 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5355. Min Range: -4.5355
Max Act: 4.4105. Min Act: -0.1700
Data Index: 1707464 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5355. Min Range: -4.5355
Max Act: 4.4417. Min Act: -0.1700
Data Index: 6317395 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5355. Min Range: -4.5355
Max Act: 4.4105. Min Act: -0.1700
Data Index: 6130913 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5355. Min Range: -4.5355
Max Act: 4.4105. Min Act: -0.1700
Data Index: 824758 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5355. Min Range: -4.5355
Max Act: 4.3792. Min Act: -0.1700
Data Index: 1159509 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5355. Min Range: -4.5355
Max Act: 4.3792. Min Act: -0.1700
Data Index: 3893148 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5355. Min Range: -4.5355
Max Act: 4.4105. Min Act: -0.1700
Data Index: 7257036 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5355. Min Range: -4.5355
Max Act: 4.4105. Min Act: -0.1700
Data Index: 8179958 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5355. Min Range: -4.5355
Max Act: 4.3792. Min Act: -0.1700
Data Index: 3901058 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5355. Min Range: -4.5355
Max Act: 4.3480. Min Act: -0.1700
Data Index: 4560093 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5355. Min Range: -4.5355
Max Act: 4.3480. Min Act: -0.1700
Data Index: 784294 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5355. Min Range: -4.5355
Max Act: 4.3480. Min Act: -0.1700
Data Index: 53184 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5355. Min Range: -4.5355
Max Act: 4.3167. Min Act: -0.1700
Data Index: 6602196 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5355. Min Range: -4.5355
Max Act: 4.3480. Min Act: -0.1700
Data Index: 5799118 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5355. Min Range: -4.5355
Max Act: 4.3167. Min Act: -0.1700
Data Index: 975856 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5355. Min Range: -4.5355
Max Act: 4.3167. Min Act: -0.1700
Data Index: 322376 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5355. Min Range: -4.5355
Max Act: 4.3167. Min Act: -0.1700
Data Index: 695846 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5355. Min Range: -4.5355
Max Act: 4.3480. Min Act: -0.1700
Data Index: 3936502 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19