Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3404 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0302. Min Range: -5.0302
Max Act: 5.0302. Min Act: -0.1700
Data Index: 4248469 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0302. Min Range: -5.0302
Max Act: 5.0302. Min Act: -0.1700
Data Index: 2300489 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.9990. Min Act: -0.1700
Data Index: 6583051 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.9990. Min Act: -0.1700
Data Index: 2403953 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.9677. Min Act: -0.1700
Data Index: 623245 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.9677. Min Act: -0.1700
Data Index: 1124472 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.9365. Min Act: -0.1700
Data Index: 8031301 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.9365. Min Act: -0.1700
Data Index: 6890020 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.9052. Min Act: -0.1700
Data Index: 3817095 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.9052. Min Act: -0.1700
Data Index: 5050768 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.9052. Min Act: -0.1700
Data Index: 6369810 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.9052. Min Act: -0.1700
Data Index: 2524727 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.9052. Min Act: -0.1700
Data Index: 6947076 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.8740. Min Act: -0.1700
Data Index: 2765922 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.8740. Min Act: -0.1700
Data Index: 5039534 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.8740. Min Act: -0.1700
Data Index: 2053253 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.8740. Min Act: -0.1700
Data Index: 3837049 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.9052. Min Act: -0.1700
Data Index: 4254428 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.8427. Min Act: -0.1700
Data Index: 1204750 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.8740. Min Act: -0.1700
Data Index: 1836800 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19