Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3777 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2383. Min Range: -7.2383
Max Act: 7.2383. Min Act: -0.1700
Data Index: 1912540 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2383. Min Range: -7.2383
Max Act: 7.1445. Min Act: -0.1700
Data Index: 5246110 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2383. Min Range: -7.2383
Max Act: 7.0820. Min Act: -0.1700
Data Index: 6381307 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2383. Min Range: -7.2383
Max Act: 6.9570. Min Act: -0.1700
Data Index: 791637 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2383. Min Range: -7.2383
Max Act: 6.9258. Min Act: -0.1700
Data Index: 2215736 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2383. Min Range: -7.2383
Max Act: 6.8945. Min Act: -0.1700
Data Index: 7006530 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2383. Min Range: -7.2383
Max Act: 6.8633. Min Act: -0.1700
Data Index: 664917 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2383. Min Range: -7.2383
Max Act: 6.8320. Min Act: -0.1700
Data Index: 1101086 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2383. Min Range: -7.2383
Max Act: 6.8320. Min Act: -0.1700
Data Index: 3858558 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2383. Min Range: -7.2383
Max Act: 6.7695. Min Act: -0.1700
Data Index: 5463802 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2383. Min Range: -7.2383
Max Act: 6.8008. Min Act: -0.1700
Data Index: 4919261 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2383. Min Range: -7.2383
Max Act: 6.8008. Min Act: -0.1700
Data Index: 4048207 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2383. Min Range: -7.2383
Max Act: 6.7695. Min Act: -0.1700
Data Index: 7526042 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2383. Min Range: -7.2383
Max Act: 6.7383. Min Act: -0.1700
Data Index: 1098449 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2383. Min Range: -7.2383
Max Act: 6.7070. Min Act: -0.1700
Data Index: 5018706 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2383. Min Range: -7.2383
Max Act: 6.5820. Min Act: -0.1700
Data Index: 5966468 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2383. Min Range: -7.2383
Max Act: 6.6445. Min Act: -0.1700
Data Index: 4145141 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2383. Min Range: -7.2383
Max Act: 6.6445. Min Act: -0.1700
Data Index: 7290954 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2383. Min Range: -7.2383
Max Act: 6.6133. Min Act: -0.1700
Data Index: 6009720 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2383. Min Range: -7.2383
Max Act: 6.5820. Min Act: -0.1700
Data Index: 176836 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19