Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2073 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1950. Min Range: -7.1950
Max Act: 7.1950. Min Act: -0.1700
Data Index: 7543153 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1950. Min Range: -7.1950
Max Act: 7.1638. Min Act: -0.1700
Data Index: 7357606 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1950. Min Range: -7.1950
Max Act: 7.0700. Min Act: -0.1700
Data Index: 7887311 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1950. Min Range: -7.1950
Max Act: 7.0075. Min Act: -0.1700
Data Index: 1885199 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1950. Min Range: -7.1950
Max Act: 6.9763. Min Act: -0.1700
Data Index: 3217319 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1950. Min Range: -7.1950
Max Act: 6.9138. Min Act: -0.1700
Data Index: 932826 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1950. Min Range: -7.1950
Max Act: 6.8825. Min Act: -0.1700
Data Index: 4319941 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1950. Min Range: -7.1950
Max Act: 6.8513. Min Act: -0.1700
Data Index: 8801482 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1950. Min Range: -7.1950
Max Act: 6.8513. Min Act: -0.1700
Data Index: 6141711 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1950. Min Range: -7.1950
Max Act: 6.8200. Min Act: -0.1700
Data Index: 775196 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1950. Min Range: -7.1950
Max Act: 6.7888. Min Act: -0.1700
Data Index: 2090547 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1950. Min Range: -7.1950
Max Act: 6.7575. Min Act: -0.1700
Data Index: 4092826 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1950. Min Range: -7.1950
Max Act: 6.7263. Min Act: -0.1700
Data Index: 1548755 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1950. Min Range: -7.1950
Max Act: 6.6950. Min Act: -0.1700
Data Index: 3546069 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1950. Min Range: -7.1950
Max Act: 6.6950. Min Act: -0.1700
Data Index: 1542737 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1950. Min Range: -7.1950
Max Act: 6.7263. Min Act: -0.1700
Data Index: 7047293 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1950. Min Range: -7.1950
Max Act: 6.6638. Min Act: -0.1700
Data Index: 3474560 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1950. Min Range: -7.1950
Max Act: 6.6638. Min Act: -0.1700
Data Index: 8500085 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1950. Min Range: -7.1950
Max Act: 6.6638. Min Act: -0.1700
Data Index: 2950245 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1950. Min Range: -7.1950
Max Act: 6.6325. Min Act: -0.1700
Data Index: 4303947 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #19