Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 459 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.1204. Min Range: -13.1204
Max Act: 13.1204. Min Act: -0.1700
Data Index: 4763938 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.1204. Min Range: -13.1204
Max Act: 12.9954. Min Act: -0.1700
Data Index: 8677378 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.1204. Min Range: -13.1204
Max Act: 12.6829. Min Act: -0.1700
Data Index: 7956998 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.1204. Min Range: -13.1204
Max Act: 12.7454. Min Act: -0.1700
Data Index: 3094549 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.1204. Min Range: -13.1204
Max Act: 12.6204. Min Act: -0.1700
Data Index: 2879455 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.1204. Min Range: -13.1204
Max Act: 12.6204. Min Act: -0.1700
Data Index: 7321391 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.1204. Min Range: -13.1204
Max Act: 12.6204. Min Act: -0.1700
Data Index: 4314067 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.1204. Min Range: -13.1204
Max Act: 12.5579. Min Act: -0.1700
Data Index: 1226465 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.1204. Min Range: -13.1204
Max Act: 12.4954. Min Act: -0.1700
Data Index: 7458324 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.1204. Min Range: -13.1204
Max Act: 12.4954. Min Act: -0.1700
Data Index: 6059240 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.1204. Min Range: -13.1204
Max Act: 12.4954. Min Act: -0.1700
Data Index: 2121152 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.1204. Min Range: -13.1204
Max Act: 12.4954. Min Act: -0.1700
Data Index: 2618658 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.1204. Min Range: -13.1204
Max Act: 12.4954. Min Act: -0.1700
Data Index: 298650 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.1204. Min Range: -13.1204
Max Act: 12.3704. Min Act: -0.1700
Data Index: 3452811 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.1204. Min Range: -13.1204
Max Act: 12.3704. Min Act: -0.1700
Data Index: 7575610 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.1204. Min Range: -13.1204
Max Act: 12.3704. Min Act: -0.1700
Data Index: 7386278 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.1204. Min Range: -13.1204
Max Act: 12.3704. Min Act: -0.1700
Data Index: 4103683 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.1204. Min Range: -13.1204
Max Act: 12.3704. Min Act: -0.1700
Data Index: 8705205 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.1204. Min Range: -13.1204
Max Act: 12.3079. Min Act: -0.1700
Data Index: 1247513 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.1204. Min Range: -13.1204
Max Act: 12.3079. Min Act: -0.1700
Data Index: 3471199 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19