Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1477 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4493. Min Range: -6.4493
Max Act: 6.4493. Min Act: -0.1700
Data Index: 8595765 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4493. Min Range: -6.4493
Max Act: 6.4181. Min Act: -0.1700
Data Index: 3266504 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4493. Min Range: -6.4493
Max Act: 6.3868. Min Act: -0.1700
Data Index: 6348356 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4493. Min Range: -6.4493
Max Act: 6.3243. Min Act: -0.1700
Data Index: 1798828 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4493. Min Range: -6.4493
Max Act: 6.3243. Min Act: -0.1700
Data Index: 2840939 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4493. Min Range: -6.4493
Max Act: 6.2931. Min Act: -0.1700
Data Index: 560405 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4493. Min Range: -6.4493
Max Act: 6.1681. Min Act: -0.1700
Data Index: 283834 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4493. Min Range: -6.4493
Max Act: 6.1681. Min Act: -0.1700
Data Index: 3479882 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4493. Min Range: -6.4493
Max Act: 6.1681. Min Act: -0.1700
Data Index: 2214577 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4493. Min Range: -6.4493
Max Act: 6.1368. Min Act: -0.1700
Data Index: 4085127 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4493. Min Range: -6.4493
Max Act: 6.1368. Min Act: -0.1700
Data Index: 7140021 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4493. Min Range: -6.4493
Max Act: 6.1056. Min Act: -0.1700
Data Index: 4908898 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4493. Min Range: -6.4493
Max Act: 6.1056. Min Act: -0.1700
Data Index: 5123410 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4493. Min Range: -6.4493
Max Act: 6.0431. Min Act: -0.1700
Data Index: 3539077 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4493. Min Range: -6.4493
Max Act: 6.0743. Min Act: -0.1700
Data Index: 2535435 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4493. Min Range: -6.4493
Max Act: 6.0743. Min Act: -0.1700
Data Index: 2861849 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4493. Min Range: -6.4493
Max Act: 6.0431. Min Act: -0.1700
Data Index: 5376062 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4493. Min Range: -6.4493
Max Act: 6.0431. Min Act: -0.1700
Data Index: 7640220 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4493. Min Range: -6.4493
Max Act: 6.0431. Min Act: -0.1700
Data Index: 23695 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4493. Min Range: -6.4493
Max Act: 6.0118. Min Act: -0.1700
Data Index: 7010136 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #19