Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3327 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2670. Min Range: -5.2670
Max Act: 5.2670. Min Act: -0.1700
Data Index: 6353437 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2670. Min Range: -5.2670
Max Act: 5.2045. Min Act: -0.1700
Data Index: 3991280 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2670. Min Range: -5.2670
Max Act: 5.0795. Min Act: -0.1700
Data Index: 6774354 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2670. Min Range: -5.2670
Max Act: 5.0482. Min Act: -0.1700
Data Index: 8812419 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2670. Min Range: -5.2670
Max Act: 4.9545. Min Act: -0.1700
Data Index: 385922 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2670. Min Range: -5.2670
Max Act: 4.9545. Min Act: -0.1700
Data Index: 5908256 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2670. Min Range: -5.2670
Max Act: 4.9232. Min Act: -0.1700
Data Index: 4577287 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2670. Min Range: -5.2670
Max Act: 4.9232. Min Act: -0.1700
Data Index: 6793127 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2670. Min Range: -5.2670
Max Act: 4.8920. Min Act: -0.1700
Data Index: 5675322 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2670. Min Range: -5.2670
Max Act: 4.8920. Min Act: -0.1700
Data Index: 3030317 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2670. Min Range: -5.2670
Max Act: 4.8295. Min Act: -0.1700
Data Index: 275538 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2670. Min Range: -5.2670
Max Act: 4.8295. Min Act: -0.1700
Data Index: 1995733 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2670. Min Range: -5.2670
Max Act: 4.7670. Min Act: -0.1700
Data Index: 1276158 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2670. Min Range: -5.2670
Max Act: 4.7982. Min Act: -0.1700
Data Index: 6483815 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2670. Min Range: -5.2670
Max Act: 4.7670. Min Act: -0.1700
Data Index: 7084420 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2670. Min Range: -5.2670
Max Act: 4.7982. Min Act: -0.1700
Data Index: 3957602 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2670. Min Range: -5.2670
Max Act: 4.7670. Min Act: -0.1700
Data Index: 2038068 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2670. Min Range: -5.2670
Max Act: 4.7670. Min Act: -0.1700
Data Index: 6242519 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2670. Min Range: -5.2670
Max Act: 4.7670. Min Act: -0.1700
Data Index: 4167090 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2670. Min Range: -5.2670
Max Act: 4.7357. Min Act: -0.1700
Data Index: 6544741 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19