Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2578 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9656. Min Range: -4.9656
Max Act: 4.9656. Min Act: -0.1700
Data Index: 5389008 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9656. Min Range: -4.9656
Max Act: 4.8406. Min Act: -0.1700
Data Index: 5146338 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9656. Min Range: -4.9656
Max Act: 4.7781. Min Act: -0.1700
Data Index: 473892 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9656. Min Range: -4.9656
Max Act: 4.7469. Min Act: -0.1700
Data Index: 4019556 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9656. Min Range: -4.9656
Max Act: 4.7469. Min Act: -0.1700
Data Index: 5588441 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9656. Min Range: -4.9656
Max Act: 4.7469. Min Act: -0.1700
Data Index: 807248 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9656. Min Range: -4.9656
Max Act: 4.7156. Min Act: -0.1700
Data Index: 8032637 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9656. Min Range: -4.9656
Max Act: 4.7156. Min Act: -0.1700
Data Index: 6036330 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9656. Min Range: -4.9656
Max Act: 4.7156. Min Act: -0.1700
Data Index: 3469993 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9656. Min Range: -4.9656
Max Act: 4.6843. Min Act: -0.1700
Data Index: 7110856 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9656. Min Range: -4.9656
Max Act: 4.6843. Min Act: -0.1700
Data Index: 5435036 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9656. Min Range: -4.9656
Max Act: 4.6531. Min Act: -0.1700
Data Index: 1049791 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9656. Min Range: -4.9656
Max Act: 4.6843. Min Act: -0.1700
Data Index: 7963684 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9656. Min Range: -4.9656
Max Act: 4.6531. Min Act: -0.1700
Data Index: 6170474 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9656. Min Range: -4.9656
Max Act: 4.6843. Min Act: -0.1700
Data Index: 6274694 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9656. Min Range: -4.9656
Max Act: 4.6218. Min Act: -0.1700
Data Index: 1011602 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9656. Min Range: -4.9656
Max Act: 4.6218. Min Act: -0.1700
Data Index: 3954305 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9656. Min Range: -4.9656
Max Act: 4.6218. Min Act: -0.1700
Data Index: 3987127 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9656. Min Range: -4.9656
Max Act: 4.5906. Min Act: -0.1700
Data Index: 4017325 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9656. Min Range: -4.9656
Max Act: 4.6218. Min Act: -0.1700
Data Index: 6293654 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19