Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4011 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5675. Min Range: -3.5675
Max Act: 3.5675. Min Act: -0.1700
Data Index: 3133115 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5675. Min Range: -3.5675
Max Act: 3.5206. Min Act: -0.1700
Data Index: 3528317 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5675. Min Range: -3.5675
Max Act: 3.5049. Min Act: -0.1700
Data Index: 5832800 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5675. Min Range: -3.5675
Max Act: 3.5049. Min Act: -0.1700
Data Index: 4067846 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5675. Min Range: -3.5675
Max Act: 3.4579. Min Act: -0.1700
Data Index: 7631106 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5675. Min Range: -3.5675
Max Act: 3.4422. Min Act: -0.1700
Data Index: 92211 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5675. Min Range: -3.5675
Max Act: 3.4892. Min Act: -0.1700
Data Index: 953708 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5675. Min Range: -3.5675
Max Act: 3.4579. Min Act: -0.1700
Data Index: 5466699 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5675. Min Range: -3.5675
Max Act: 3.4736. Min Act: -0.1700
Data Index: 7184093 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5675. Min Range: -3.5675
Max Act: 3.4736. Min Act: -0.1700
Data Index: 7141565 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5675. Min Range: -3.5675
Max Act: 3.4579. Min Act: -0.1700
Data Index: 3015203 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5675. Min Range: -3.5675
Max Act: 3.4579. Min Act: -0.1700
Data Index: 6883968 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5675. Min Range: -3.5675
Max Act: 3.4266. Min Act: -0.1700
Data Index: 3370344 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5675. Min Range: -3.5675
Max Act: 3.4266. Min Act: -0.1700
Data Index: 8041755 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5675. Min Range: -3.5675
Max Act: 3.4422. Min Act: -0.1700
Data Index: 2642988 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5675. Min Range: -3.5675
Max Act: 3.4266. Min Act: -0.1700
Data Index: 6013319 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5675. Min Range: -3.5675
Max Act: 3.4266. Min Act: -0.1700
Data Index: 6801008 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5675. Min Range: -3.5675
Max Act: 3.4422. Min Act: -0.1700
Data Index: 7363275 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5675. Min Range: -3.5675
Max Act: 3.4266. Min Act: -0.1700
Data Index: 4205441 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5675. Min Range: -3.5675
Max Act: 3.4109. Min Act: -0.1700
Data Index: 5539289 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19