Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1595 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1444. Min Range: -6.1444
Max Act: 6.1444. Min Act: -0.1700
Data Index: 2898860 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1444. Min Range: -6.1444
Max Act: 5.8944. Min Act: -0.1700
Data Index: 1339489 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1444. Min Range: -6.1444
Max Act: 5.8319. Min Act: -0.1700
Data Index: 1002039 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1444. Min Range: -6.1444
Max Act: 5.7694. Min Act: -0.1700
Data Index: 8814565 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1444. Min Range: -6.1444
Max Act: 5.6757. Min Act: -0.1700
Data Index: 1101529 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1444. Min Range: -6.1444
Max Act: 5.7069. Min Act: -0.1700
Data Index: 7855547 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1444. Min Range: -6.1444
Max Act: 5.7069. Min Act: -0.1700
Data Index: 153861 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1444. Min Range: -6.1444
Max Act: 5.6757. Min Act: -0.1700
Data Index: 5490406 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1444. Min Range: -6.1444
Max Act: 5.6132. Min Act: -0.1700
Data Index: 8126892 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1444. Min Range: -6.1444
Max Act: 5.6444. Min Act: -0.1700
Data Index: 22035 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1444. Min Range: -6.1444
Max Act: 5.6132. Min Act: -0.1700
Data Index: 8028411 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1444. Min Range: -6.1444
Max Act: 5.5819. Min Act: -0.1700
Data Index: 5598763 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1444. Min Range: -6.1444
Max Act: 5.5819. Min Act: -0.1700
Data Index: 3858444 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1444. Min Range: -6.1444
Max Act: 5.5819. Min Act: -0.1700
Data Index: 7520666 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1444. Min Range: -6.1444
Max Act: 5.5819. Min Act: -0.1700
Data Index: 3289131 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1444. Min Range: -6.1444
Max Act: 5.5819. Min Act: -0.1700
Data Index: 2356922 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1444. Min Range: -6.1444
Max Act: 5.5507. Min Act: -0.1700
Data Index: 5979641 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1444. Min Range: -6.1444
Max Act: 5.5507. Min Act: -0.1700
Data Index: 7959617 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1444. Min Range: -6.1444
Max Act: 5.5194. Min Act: -0.1700
Data Index: 663804 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1444. Min Range: -6.1444
Max Act: 5.5507. Min Act: -0.1700
Data Index: 5457666 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #19