Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1951 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7976. Min Range: -4.7976
Max Act: 4.7976. Min Act: -0.1700
Data Index: 7646735 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7976. Min Range: -4.7976
Max Act: 4.7351. Min Act: -0.1700
Data Index: 1173356 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7976. Min Range: -4.7976
Max Act: 4.7351. Min Act: -0.1700
Data Index: 5288070 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7976. Min Range: -4.7976
Max Act: 4.6726. Min Act: -0.1700
Data Index: 3729246 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7976. Min Range: -4.7976
Max Act: 4.6413. Min Act: -0.1700
Data Index: 8200733 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7976. Min Range: -4.7976
Max Act: 4.6413. Min Act: -0.1700
Data Index: 2293813 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7976. Min Range: -4.7976
Max Act: 4.6413. Min Act: -0.1700
Data Index: 4315498 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7976. Min Range: -4.7976
Max Act: 4.6101. Min Act: -0.1700
Data Index: 5703451 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7976. Min Range: -4.7976
Max Act: 4.5788. Min Act: -0.1700
Data Index: 2140825 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7976. Min Range: -4.7976
Max Act: 4.5788. Min Act: -0.1700
Data Index: 5735283 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7976. Min Range: -4.7976
Max Act: 4.5476. Min Act: -0.1700
Data Index: 2263517 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7976. Min Range: -4.7976
Max Act: 4.5476. Min Act: -0.1700
Data Index: 230333 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7976. Min Range: -4.7976
Max Act: 4.5476. Min Act: -0.1700
Data Index: 459883 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7976. Min Range: -4.7976
Max Act: 4.5476. Min Act: -0.1700
Data Index: 4514998 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7976. Min Range: -4.7976
Max Act: 4.5163. Min Act: -0.1700
Data Index: 8072252 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7976. Min Range: -4.7976
Max Act: 4.5476. Min Act: -0.1700
Data Index: 1167848 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7976. Min Range: -4.7976
Max Act: 4.4851. Min Act: -0.1700
Data Index: 5967643 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7976. Min Range: -4.7976
Max Act: 4.5788. Min Act: -0.1700
Data Index: 1450816 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7976. Min Range: -4.7976
Max Act: 4.4851. Min Act: -0.1700
Data Index: 8300317 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7976. Min Range: -4.7976
Max Act: 4.4851. Min Act: -0.1700
Data Index: 5735282 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19