Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3631 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3755. Min Range: -8.3755
Max Act: 8.3755. Min Act: -0.1700
Data Index: 3153536 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3755. Min Range: -8.3755
Max Act: 8.2505. Min Act: -0.1700
Data Index: 7691743 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3755. Min Range: -8.3755
Max Act: 8.1255. Min Act: -0.1700
Data Index: 6798831 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3755. Min Range: -8.3755
Max Act: 8.0630. Min Act: -0.1700
Data Index: 8617493 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3755. Min Range: -8.3755
Max Act: 7.9380. Min Act: -0.1700
Data Index: 82783 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3755. Min Range: -8.3755
Max Act: 7.8755. Min Act: -0.1700
Data Index: 5215089 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3755. Min Range: -8.3755
Max Act: 7.8755. Min Act: -0.1700
Data Index: 506189 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3755. Min Range: -8.3755
Max Act: 7.8755. Min Act: -0.1700
Data Index: 7232313 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3755. Min Range: -8.3755
Max Act: 7.7505. Min Act: -0.1700
Data Index: 8605740 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3755. Min Range: -8.3755
Max Act: 7.8130. Min Act: -0.1700
Data Index: 8250476 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3755. Min Range: -8.3755
Max Act: 7.6880. Min Act: -0.1700
Data Index: 2961049 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3755. Min Range: -8.3755
Max Act: 7.6880. Min Act: -0.1700
Data Index: 3225529 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3755. Min Range: -8.3755
Max Act: 7.6880. Min Act: -0.1700
Data Index: 974994 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3755. Min Range: -8.3755
Max Act: 7.6880. Min Act: -0.1700
Data Index: 4004436 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3755. Min Range: -8.3755
Max Act: 7.6880. Min Act: -0.1700
Data Index: 7295026 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3755. Min Range: -8.3755
Max Act: 7.6880. Min Act: -0.1700
Data Index: 1788998 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3755. Min Range: -8.3755
Max Act: 7.6880. Min Act: -0.1700
Data Index: 4008425 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3755. Min Range: -8.3755
Max Act: 7.6880. Min Act: -0.1700
Data Index: 524972 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3755. Min Range: -8.3755
Max Act: 7.6255. Min Act: -0.1700
Data Index: 4397295 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3755. Min Range: -8.3755
Max Act: 7.6255. Min Act: -0.1700
Data Index: 917853 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19