Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3037 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.4720. Min Range: -10.4720
Max Act: 10.4720. Min Act: -0.1700
Data Index: 3482648 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4720. Min Range: -10.4720
Max Act: 9.9720. Min Act: -0.1700
Data Index: 1025336 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4720. Min Range: -10.4720
Max Act: 9.9095. Min Act: -0.1700
Data Index: 83982 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4720. Min Range: -10.4720
Max Act: 9.2845. Min Act: -0.1700
Data Index: 2700439 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4720. Min Range: -10.4720
Max Act: 9.0345. Min Act: -0.1700
Data Index: 1299274 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4720. Min Range: -10.4720
Max Act: 9.0970. Min Act: -0.1700
Data Index: 3464148 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4720. Min Range: -10.4720
Max Act: 7.9095. Min Act: -0.1700
Data Index: 3438437 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4720. Min Range: -10.4720
Max Act: 8.7845. Min Act: -0.1700
Data Index: 8174104 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4720. Min Range: -10.4720
Max Act: 8.9095. Min Act: -0.1700
Data Index: 6837759 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4720. Min Range: -10.4720
Max Act: 8.9095. Min Act: -0.1700
Data Index: 2148314 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4720. Min Range: -10.4720
Max Act: 8.7845. Min Act: -0.1700
Data Index: 619260 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4720. Min Range: -10.4720
Max Act: 8.8470. Min Act: -0.1700
Data Index: 4668435 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4720. Min Range: -10.4720
Max Act: 8.9095. Min Act: -0.1700
Data Index: 8612469 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4720. Min Range: -10.4720
Max Act: 8.9720. Min Act: -0.1700
Data Index: 1205181 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4720. Min Range: -10.4720
Max Act: 7.5657. Min Act: -0.1700
Data Index: 5556836 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4720. Min Range: -10.4720
Max Act: 8.7845. Min Act: -0.1700
Data Index: 194186 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4720. Min Range: -10.4720
Max Act: 8.4095. Min Act: -0.1700
Data Index: 4191816 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4720. Min Range: -10.4720
Max Act: 8.9095. Min Act: -0.1700
Data Index: 4052044 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4720. Min Range: -10.4720
Max Act: 8.8470. Min Act: -0.1700
Data Index: 2391656 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4720. Min Range: -10.4720
Max Act: 8.9095. Min Act: -0.1700
Data Index: 4684295 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19