Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3268 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8423. Min Range: -7.8423
Max Act: 7.8423. Min Act: -0.1700
Data Index: 4630697 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8423. Min Range: -7.8423
Max Act: 7.6548. Min Act: -0.1700
Data Index: 2110942 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8423. Min Range: -7.8423
Max Act: 7.6548. Min Act: -0.1700
Data Index: 8116153 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8423. Min Range: -7.8423
Max Act: 7.5923. Min Act: -0.1700
Data Index: 522799 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8423. Min Range: -7.8423
Max Act: 7.4985. Min Act: -0.1700
Data Index: 7385199 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8423. Min Range: -7.8423
Max Act: 7.4048. Min Act: -0.1700
Data Index: 657023 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8423. Min Range: -7.8423
Max Act: 7.4048. Min Act: -0.1700
Data Index: 1027962 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8423. Min Range: -7.8423
Max Act: 7.3423. Min Act: -0.1700
Data Index: 4840431 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8423. Min Range: -7.8423
Max Act: 7.3110. Min Act: -0.1700
Data Index: 8116155 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8423. Min Range: -7.8423
Max Act: 7.2798. Min Act: -0.1700
Data Index: 2742224 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8423. Min Range: -7.8423
Max Act: 7.2798. Min Act: -0.1700
Data Index: 7510212 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8423. Min Range: -7.8423
Max Act: 7.2798. Min Act: -0.1700
Data Index: 634085 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8423. Min Range: -7.8423
Max Act: 7.2485. Min Act: -0.1700
Data Index: 2095227 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8423. Min Range: -7.8423
Max Act: 7.2173. Min Act: -0.1700
Data Index: 6415755 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8423. Min Range: -7.8423
Max Act: 7.1860. Min Act: -0.1700
Data Index: 2003149 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8423. Min Range: -7.8423
Max Act: 7.1860. Min Act: -0.1700
Data Index: 8352198 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8423. Min Range: -7.8423
Max Act: 7.1860. Min Act: -0.1700
Data Index: 5759043 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8423. Min Range: -7.8423
Max Act: 7.1548. Min Act: -0.1700
Data Index: 3624791 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8423. Min Range: -7.8423
Max Act: 7.1235. Min Act: -0.1700
Data Index: 486728 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8423. Min Range: -7.8423
Max Act: 7.1235. Min Act: -0.1700
Data Index: 8116154 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19