Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2820 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1407. Min Range: -4.1407
Max Act: 4.1407. Min Act: -0.1700
Data Index: 2100117 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1407. Min Range: -4.1407
Max Act: 4.0469. Min Act: -0.1700
Data Index: 6673436 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1407. Min Range: -4.1407
Max Act: 4.0782. Min Act: -0.1700
Data Index: 1682606 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1407. Min Range: -4.1407
Max Act: 3.9844. Min Act: -0.1700
Data Index: 2075026 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1407. Min Range: -4.1407
Max Act: 3.9844. Min Act: -0.1700
Data Index: 7511616 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1407. Min Range: -4.1407
Max Act: 3.9844. Min Act: -0.1700
Data Index: 4028441 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1407. Min Range: -4.1407
Max Act: 3.9844. Min Act: -0.1700
Data Index: 8445587 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1407. Min Range: -4.1407
Max Act: 3.9532. Min Act: -0.1700
Data Index: 4331675 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1407. Min Range: -4.1407
Max Act: 3.9532. Min Act: -0.1700
Data Index: 2584379 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1407. Min Range: -4.1407
Max Act: 3.9219. Min Act: -0.1700
Data Index: 5288902 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1407. Min Range: -4.1407
Max Act: 3.9219. Min Act: -0.1700
Data Index: 1784350 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1407. Min Range: -4.1407
Max Act: 3.9219. Min Act: -0.1700
Data Index: 4787803 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1407. Min Range: -4.1407
Max Act: 3.9219. Min Act: -0.1700
Data Index: 295372 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1407. Min Range: -4.1407
Max Act: 3.8906. Min Act: -0.1700
Data Index: 4873940 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1407. Min Range: -4.1407
Max Act: 3.8906. Min Act: -0.1700
Data Index: 1988834 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1407. Min Range: -4.1407
Max Act: 3.8906. Min Act: -0.1700
Data Index: 7845509 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1407. Min Range: -4.1407
Max Act: 3.8594. Min Act: -0.1700
Data Index: 4659414 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1407. Min Range: -4.1407
Max Act: 3.8906. Min Act: -0.1700
Data Index: 7125781 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1407. Min Range: -4.1407
Max Act: 3.8906. Min Act: -0.1700
Data Index: 794944 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1407. Min Range: -4.1407
Max Act: 3.8594. Min Act: -0.1700
Data Index: 966392 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19