Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4022 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.6350. Min Act: -0.1700
Data Index: 7683108 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.5413. Min Act: -0.1700
Data Index: 4786363 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.4788. Min Act: -0.1700
Data Index: 2669416 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.4788. Min Act: -0.1700
Data Index: 6971484 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.4788. Min Act: -0.1700
Data Index: 679559 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.4475. Min Act: -0.1700
Data Index: 3834312 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.4475. Min Act: -0.1700
Data Index: 7977199 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.4475. Min Act: -0.1700
Data Index: 8454162 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.4475. Min Act: -0.1700
Data Index: 7178290 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.4475. Min Act: -0.1700
Data Index: 4684769 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.4163. Min Act: -0.1700
Data Index: 11632 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.4163. Min Act: -0.1700
Data Index: 6314240 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.4163. Min Act: -0.1700
Data Index: 2560891 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.4163. Min Act: -0.1700
Data Index: 7888498 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.4163. Min Act: -0.1700
Data Index: 3355571 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.3850. Min Act: -0.1700
Data Index: 1433334 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.3850. Min Act: -0.1700
Data Index: 2078252 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.4163. Min Act: -0.1700
Data Index: 7620257 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.3850. Min Act: -0.1700
Data Index: 7404281 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.3850. Min Act: -0.1700
Data Index: 5068133 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19