Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 874 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9377. Min Range: -6.9377
Max Act: 6.9377. Min Act: -0.1700
Data Index: 5454291 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9377. Min Range: -6.9377
Max Act: 6.9377. Min Act: -0.1700
Data Index: 6679777 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9377. Min Range: -6.9377
Max Act: 6.8440. Min Act: -0.1700
Data Index: 4874737 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9377. Min Range: -6.9377
Max Act: 6.8440. Min Act: -0.1700
Data Index: 2968799 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9377. Min Range: -6.9377
Max Act: 6.7502. Min Act: -0.1700
Data Index: 2377444 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9377. Min Range: -6.9377
Max Act: 6.6877. Min Act: -0.1700
Data Index: 7508020 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9377. Min Range: -6.9377
Max Act: 6.7190. Min Act: -0.1700
Data Index: 2405810 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9377. Min Range: -6.9377
Max Act: 6.7502. Min Act: -0.1700
Data Index: 2713552 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9377. Min Range: -6.9377
Max Act: 6.6877. Min Act: -0.1700
Data Index: 2511966 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9377. Min Range: -6.9377
Max Act: 6.6252. Min Act: -0.1700
Data Index: 354702 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9377. Min Range: -6.9377
Max Act: 6.5627. Min Act: -0.1700
Data Index: 8168533 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9377. Min Range: -6.9377
Max Act: 6.5627. Min Act: -0.1700
Data Index: 8699299 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9377. Min Range: -6.9377
Max Act: 6.5002. Min Act: -0.1700
Data Index: 5130568 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9377. Min Range: -6.9377
Max Act: 6.5315. Min Act: -0.1700
Data Index: 6262217 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9377. Min Range: -6.9377
Max Act: 6.5315. Min Act: -0.1700
Data Index: 1555736 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9377. Min Range: -6.9377
Max Act: 6.5315. Min Act: -0.1700
Data Index: 2659075 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9377. Min Range: -6.9377
Max Act: 6.5315. Min Act: -0.1700
Data Index: 8188599 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9377. Min Range: -6.9377
Max Act: 6.4690. Min Act: -0.1700
Data Index: 1032971 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9377. Min Range: -6.9377
Max Act: 6.5002. Min Act: -0.1700
Data Index: 1962590 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9377. Min Range: -6.9377
Max Act: 6.4690. Min Act: -0.1700
Data Index: 1032969 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19