Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2585 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2175. Min Range: -4.2175
Max Act: 4.2175. Min Act: -0.1700
Data Index: 1662685 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2175. Min Range: -4.2175
Max Act: 4.1238. Min Act: -0.1700
Data Index: 3485591 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2175. Min Range: -4.2175
Max Act: 4.0925. Min Act: -0.1700
Data Index: 708952 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2175. Min Range: -4.2175
Max Act: 4.0925. Min Act: -0.1700
Data Index: 1431458 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2175. Min Range: -4.2175
Max Act: 4.0612. Min Act: -0.1700
Data Index: 7696733 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2175. Min Range: -4.2175
Max Act: 3.9987. Min Act: -0.1700
Data Index: 7875773 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2175. Min Range: -4.2175
Max Act: 3.9987. Min Act: -0.1700
Data Index: 5829305 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2175. Min Range: -4.2175
Max Act: 3.9987. Min Act: -0.1700
Data Index: 4559721 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2175. Min Range: -4.2175
Max Act: 3.9362. Min Act: -0.1700
Data Index: 172581 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2175. Min Range: -4.2175
Max Act: 3.9362. Min Act: -0.1700
Data Index: 7756697 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2175. Min Range: -4.2175
Max Act: 3.9362. Min Act: -0.1700
Data Index: 5132849 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2175. Min Range: -4.2175
Max Act: 3.9049. Min Act: -0.1700
Data Index: 6114675 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2175. Min Range: -4.2175
Max Act: 3.8737. Min Act: -0.1700
Data Index: 3254340 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2175. Min Range: -4.2175
Max Act: 3.9049. Min Act: -0.1700
Data Index: 3286729 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2175. Min Range: -4.2175
Max Act: 3.9362. Min Act: -0.1700
Data Index: 2440534 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2175. Min Range: -4.2175
Max Act: 3.8737. Min Act: -0.1700
Data Index: 6055147 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2175. Min Range: -4.2175
Max Act: 3.8424. Min Act: -0.1700
Data Index: 8172318 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2175. Min Range: -4.2175
Max Act: 3.8424. Min Act: -0.1700
Data Index: 1747244 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2175. Min Range: -4.2175
Max Act: 3.8737. Min Act: -0.1700
Data Index: 8016509 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2175. Min Range: -4.2175
Max Act: 3.8424. Min Act: -0.1700
Data Index: 1861500 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19