Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1506 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1446. Min Range: -4.1446
Max Act: 4.1446. Min Act: -0.1700
Data Index: 1538136 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1446. Min Range: -4.1446
Max Act: 3.9571. Min Act: -0.1700
Data Index: 1088407 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1446. Min Range: -4.1446
Max Act: 3.8007. Min Act: -0.1700
Data Index: 825802 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1446. Min Range: -4.1446
Max Act: 3.7695. Min Act: -0.1700
Data Index: 7661496 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1446. Min Range: -4.1446
Max Act: 3.7226. Min Act: -0.1700
Data Index: 8201919 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1446. Min Range: -4.1446
Max Act: 3.7226. Min Act: -0.1700
Data Index: 2578839 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1446. Min Range: -4.1446
Max Act: 3.6756. Min Act: -0.1700
Data Index: 1551116 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1446. Min Range: -4.1446
Max Act: 3.6756. Min Act: -0.1700
Data Index: 5423389 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1446. Min Range: -4.1446
Max Act: 3.6443. Min Act: -0.1700
Data Index: 4840175 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1446. Min Range: -4.1446
Max Act: 3.6443. Min Act: -0.1700
Data Index: 856487 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1446. Min Range: -4.1446
Max Act: 3.6287. Min Act: -0.1700
Data Index: 3111589 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1446. Min Range: -4.1446
Max Act: 3.6287. Min Act: -0.1700
Data Index: 6158207 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1446. Min Range: -4.1446
Max Act: 3.6443. Min Act: -0.1700
Data Index: 8262205 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1446. Min Range: -4.1446
Max Act: 3.6130. Min Act: -0.1700
Data Index: 2284355 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1446. Min Range: -4.1446
Max Act: 3.6130. Min Act: -0.1700
Data Index: 4139873 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1446. Min Range: -4.1446
Max Act: 3.5974. Min Act: -0.1700
Data Index: 2229375 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1446. Min Range: -4.1446
Max Act: 3.5974. Min Act: -0.1700
Data Index: 3423135 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1446. Min Range: -4.1446
Max Act: 3.5974. Min Act: -0.1700
Data Index: 2527193 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1446. Min Range: -4.1446
Max Act: 3.5661. Min Act: -0.1700
Data Index: 7080923 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1446. Min Range: -4.1446
Max Act: 3.5817. Min Act: -0.1700
Data Index: 1078906 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19