Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1514 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2403. Min Range: -6.2403
Max Act: 6.2403. Min Act: -0.1700
Data Index: 2042753 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.7403. Min Act: -0.1700
Data Index: 124516 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.5528. Min Act: -0.1700
Data Index: 3996011 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.5216. Min Act: -0.1700
Data Index: 6142683 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.5216. Min Act: -0.1700
Data Index: 7546460 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.5528. Min Act: -0.1700
Data Index: 7668014 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.5216. Min Act: -0.1700
Data Index: 3436901 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.4591. Min Act: -0.1700
Data Index: 5493599 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.3966. Min Act: -0.1700
Data Index: 2336106 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.4278. Min Act: -0.1700
Data Index: 6675671 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.4278. Min Act: -0.1700
Data Index: 4329712 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.3966. Min Act: -0.1700
Data Index: 6988993 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.3966. Min Act: -0.1700
Data Index: 8717171 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.3341. Min Act: -0.1700
Data Index: 4020214 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.3653. Min Act: -0.1700
Data Index: 3276790 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.3341. Min Act: -0.1700
Data Index: 8382892 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.2403. Min Act: -0.1700
Data Index: 858591 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.2716. Min Act: -0.1700
Data Index: 2460398 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.2716. Min Act: -0.1700
Data Index: 7284947 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.2716. Min Act: -0.1700
Data Index: 1421378 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19