Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3630 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7403. Min Range: -6.7403
Max Act: 6.7403. Min Act: -0.1700
Data Index: 6077568 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7403. Min Range: -6.7403
Max Act: 6.5841. Min Act: -0.1700
Data Index: 2837699 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7403. Min Range: -6.7403
Max Act: 6.4903. Min Act: -0.1700
Data Index: 1207453 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7403. Min Range: -6.7403
Max Act: 6.4903. Min Act: -0.1700
Data Index: 7782656 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7403. Min Range: -6.7403
Max Act: 6.4591. Min Act: -0.1700
Data Index: 3226470 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7403. Min Range: -6.7403
Max Act: 6.4591. Min Act: -0.1700
Data Index: 6540341 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7403. Min Range: -6.7403
Max Act: 6.4278. Min Act: -0.1700
Data Index: 148470 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7403. Min Range: -6.7403
Max Act: 6.4278. Min Act: -0.1700
Data Index: 3111038 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7403. Min Range: -6.7403
Max Act: 6.3966. Min Act: -0.1700
Data Index: 2024151 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7403. Min Range: -6.7403
Max Act: 6.3653. Min Act: -0.1700
Data Index: 4191222 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7403. Min Range: -6.7403
Max Act: 6.3966. Min Act: -0.1700
Data Index: 2435559 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7403. Min Range: -6.7403
Max Act: 6.3341. Min Act: -0.1700
Data Index: 1554609 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7403. Min Range: -6.7403
Max Act: 6.3341. Min Act: -0.1700
Data Index: 5346699 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7403. Min Range: -6.7403
Max Act: 6.3028. Min Act: -0.1700
Data Index: 7485535 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7403. Min Range: -6.7403
Max Act: 6.3028. Min Act: -0.1700
Data Index: 2599437 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7403. Min Range: -6.7403
Max Act: 6.3028. Min Act: -0.1700
Data Index: 8010186 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7403. Min Range: -6.7403
Max Act: 6.3028. Min Act: -0.1700
Data Index: 8506822 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7403. Min Range: -6.7403
Max Act: 6.2716. Min Act: -0.1700
Data Index: 5584283 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7403. Min Range: -6.7403
Max Act: 6.2716. Min Act: -0.1700
Data Index: 5155526 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7403. Min Range: -6.7403
Max Act: 6.2716. Min Act: -0.1700
Data Index: 4454964 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19