Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2665 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.5825. Min Range: -1.5825
Max Act: 1.5825. Min Act: -0.1697
Data Index: 5359348 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5825. Min Range: -1.5825
Max Act: 1.4069. Min Act: -0.1698
Data Index: 856665 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5825. Min Range: -1.5825
Max Act: 1.3893. Min Act: -0.1691
Data Index: 6341006 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5825. Min Range: -1.5825
Max Act: 1.3717. Min Act: -0.1697
Data Index: 4468009 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5825. Min Range: -1.5825
Max Act: 1.3893. Min Act: -0.1700
Data Index: 8265983 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5825. Min Range: -1.5825
Max Act: 1.3540. Min Act: -0.1700
Data Index: 4233770 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5825. Min Range: -1.5825
Max Act: 1.3540. Min Act: -0.1691
Data Index: 2216185 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5825. Min Range: -1.5825
Max Act: 1.3187. Min Act: -0.1700
Data Index: 1001300 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5825. Min Range: -1.5825
Max Act: 1.2835. Min Act: -0.1699
Data Index: 6398150 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5825. Min Range: -1.5825
Max Act: 1.3011. Min Act: -0.1700
Data Index: 4996318 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5825. Min Range: -1.5825
Max Act: 1.3011. Min Act: -0.1700
Data Index: 3905266 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5825. Min Range: -1.5825
Max Act: 1.2835. Min Act: -0.1700
Data Index: 6058509 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5825. Min Range: -1.5825
Max Act: 1.2658. Min Act: -0.1699
Data Index: 2091577 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5825. Min Range: -1.5825
Max Act: 1.2835. Min Act: -0.1700
Data Index: 410631 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5825. Min Range: -1.5825
Max Act: 1.2835. Min Act: -0.1699
Data Index: 6563759 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5825. Min Range: -1.5825
Max Act: 1.2835. Min Act: -0.1698
Data Index: 4127253 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5825. Min Range: -1.5825
Max Act: 1.2482. Min Act: -0.1698
Data Index: 254713 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5825. Min Range: -1.5825
Max Act: 1.2658. Min Act: -0.1699
Data Index: 6113604 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5825. Min Range: -1.5825
Max Act: 1.2482. Min Act: -0.1699
Data Index: 7703693 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5825. Min Range: -1.5825
Max Act: 1.2482. Min Act: -0.1690
Data Index: 6563958 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19