Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2688 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1443. Min Range: -7.1443
Max Act: 7.1443. Min Act: -0.1700
Data Index: 935854 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1443. Min Range: -7.1443
Max Act: 7.0193. Min Act: -0.1700
Data Index: 3790769 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.8630. Min Act: -0.1700
Data Index: 8657951 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.8630. Min Act: -0.1700
Data Index: 7760994 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.8005. Min Act: -0.1700
Data Index: 3967503 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.7380. Min Act: -0.1700
Data Index: 5244249 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.7068. Min Act: -0.1700
Data Index: 697040 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.6755. Min Act: -0.1700
Data Index: 6715862 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.6755. Min Act: -0.1700
Data Index: 1089224 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.6755. Min Act: -0.1700
Data Index: 7422584 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.6755. Min Act: -0.1700
Data Index: 8771752 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.5505. Min Act: -0.1700
Data Index: 8723914 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.5193. Min Act: -0.1700
Data Index: 8178845 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.4880. Min Act: -0.1700
Data Index: 480368 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.4880. Min Act: -0.1700
Data Index: 971275 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.4880. Min Act: -0.1700
Data Index: 419397 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.4880. Min Act: -0.1700
Data Index: 1756253 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.4568. Min Act: -0.1700
Data Index: 3348079 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.3943. Min Act: -0.1700
Data Index: 6960971 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.4255. Min Act: -0.1700
Data Index: 5649030 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19