Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4088 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6351. Min Range: -3.6351
Max Act: 3.6351. Min Act: -0.1700
Data Index: 4985825 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6351. Min Range: -3.6351
Max Act: 3.5099. Min Act: -0.1700
Data Index: 1168833 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6351. Min Range: -3.6351
Max Act: 3.4942. Min Act: -0.1700
Data Index: 1546690 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6351. Min Range: -3.6351
Max Act: 3.4315. Min Act: -0.1700
Data Index: 3272484 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6351. Min Range: -3.6351
Max Act: 3.3218. Min Act: -0.1700
Data Index: 7404319 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6351. Min Range: -3.6351
Max Act: 3.2432. Min Act: -0.1700
Data Index: 2513372 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6351. Min Range: -3.6351
Max Act: 3.1961. Min Act: -0.1700
Data Index: 7360416 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6351. Min Range: -3.6351
Max Act: 3.1174. Min Act: -0.1700
Data Index: 8800521 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6351. Min Range: -3.6351
Max Act: 3.1961. Min Act: -0.1700
Data Index: 194673 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6351. Min Range: -3.6351
Max Act: 3.2275. Min Act: -0.1700
Data Index: 8763939 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6351. Min Range: -3.6351
Max Act: 3.1646. Min Act: -0.1700
Data Index: 2902855 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6351. Min Range: -3.6351
Max Act: 3.0543. Min Act: -0.1700
Data Index: 5627296 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6351. Min Range: -3.6351
Max Act: 3.1489. Min Act: -0.1700
Data Index: 5059387 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6351. Min Range: -3.6351
Max Act: 3.0227. Min Act: -0.1700
Data Index: 917932 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6351. Min Range: -3.6351
Max Act: 3.1016. Min Act: -0.1700
Data Index: 2931399 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6351. Min Range: -3.6351
Max Act: 3.0385. Min Act: -0.1700
Data Index: 4144664 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6351. Min Range: -3.6351
Max Act: 2.9911. Min Act: -0.1700
Data Index: 3559833 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6351. Min Range: -3.6351
Max Act: 3.0070. Min Act: -0.1700
Data Index: 4060526 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6351. Min Range: -3.6351
Max Act: 2.9911. Min Act: -0.1700
Data Index: 462256 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6351. Min Range: -3.6351
Max Act: 3.0385. Min Act: -0.1700
Data Index: 3644801 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19