Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2679 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6443. Min Range: -5.6443
Max Act: 5.6443. Min Act: -0.1700
Data Index: 5473540 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6443. Min Range: -5.6443
Max Act: 5.4881. Min Act: -0.1700
Data Index: 163623 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6443. Min Range: -5.6443
Max Act: 5.3631. Min Act: -0.1700
Data Index: 7458416 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6443. Min Range: -5.6443
Max Act: 5.3318. Min Act: -0.1700
Data Index: 2845899 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6443. Min Range: -5.6443
Max Act: 5.3318. Min Act: -0.1700
Data Index: 2535937 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6443. Min Range: -5.6443
Max Act: 5.2693. Min Act: -0.1700
Data Index: 6219145 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6443. Min Range: -5.6443
Max Act: 5.2693. Min Act: -0.1700
Data Index: 2389780 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6443. Min Range: -5.6443
Max Act: 5.2381. Min Act: -0.1700
Data Index: 7391497 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6443. Min Range: -5.6443
Max Act: 5.2381. Min Act: -0.1700
Data Index: 5541171 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6443. Min Range: -5.6443
Max Act: 5.2693. Min Act: -0.1700
Data Index: 6274090 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6443. Min Range: -5.6443
Max Act: 5.1756. Min Act: -0.1700
Data Index: 1027542 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6443. Min Range: -5.6443
Max Act: 5.2068. Min Act: -0.1700
Data Index: 3012424 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6443. Min Range: -5.6443
Max Act: 5.1756. Min Act: -0.1700
Data Index: 3741988 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6443. Min Range: -5.6443
Max Act: 5.1756. Min Act: -0.1700
Data Index: 5341438 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6443. Min Range: -5.6443
Max Act: 5.1756. Min Act: -0.1700
Data Index: 7020580 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6443. Min Range: -5.6443
Max Act: 5.1756. Min Act: -0.1700
Data Index: 7910518 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6443. Min Range: -5.6443
Max Act: 5.1756. Min Act: -0.1700
Data Index: 779287 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6443. Min Range: -5.6443
Max Act: 5.1756. Min Act: -0.1700
Data Index: 4250018 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6443. Min Range: -5.6443
Max Act: 5.1131. Min Act: -0.1700
Data Index: 3280881 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6443. Min Range: -5.6443
Max Act: 5.1131. Min Act: -0.1700
Data Index: 5937860 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19