Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 854 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.6715. Min Range: -7.6715
Max Act: 7.6715. Min Act: -0.1700
Data Index: 8302537 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6715. Min Range: -7.6715
Max Act: 7.5465. Min Act: -0.1700
Data Index: 7302227 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6715. Min Range: -7.6715
Max Act: 7.4528. Min Act: -0.1700
Data Index: 2530727 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6715. Min Range: -7.6715
Max Act: 7.4215. Min Act: -0.1700
Data Index: 8146347 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6715. Min Range: -7.6715
Max Act: 7.2965. Min Act: -0.1700
Data Index: 2530219 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6715. Min Range: -7.6715
Max Act: 7.2028. Min Act: -0.1700
Data Index: 7453029 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6715. Min Range: -7.6715
Max Act: 7.1715. Min Act: -0.1700
Data Index: 7705817 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6715. Min Range: -7.6715
Max Act: 7.1715. Min Act: -0.1700
Data Index: 6040665 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6715. Min Range: -7.6715
Max Act: 7.1403. Min Act: -0.1700
Data Index: 3326320 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6715. Min Range: -7.6715
Max Act: 7.0778. Min Act: -0.1700
Data Index: 4718557 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6715. Min Range: -7.6715
Max Act: 7.0153. Min Act: -0.1700
Data Index: 605418 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6715. Min Range: -7.6715
Max Act: 6.9840. Min Act: -0.1700
Data Index: 3756316 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6715. Min Range: -7.6715
Max Act: 6.9840. Min Act: -0.1700
Data Index: 3846197 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6715. Min Range: -7.6715
Max Act: 6.9215. Min Act: -0.1700
Data Index: 4334936 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6715. Min Range: -7.6715
Max Act: 6.9215. Min Act: -0.1700
Data Index: 6631798 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6715. Min Range: -7.6715
Max Act: 6.8903. Min Act: -0.1700
Data Index: 5026343 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6715. Min Range: -7.6715
Max Act: 6.8903. Min Act: -0.1700
Data Index: 5904456 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6715. Min Range: -7.6715
Max Act: 6.8903. Min Act: -0.1700
Data Index: 2480309 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6715. Min Range: -7.6715
Max Act: 6.8590. Min Act: -0.1700
Data Index: 2086497 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6715. Min Range: -7.6715
Max Act: 6.8590. Min Act: -0.1700
Data Index: 4018052 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #19