Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3181 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1637. Min Range: -5.1637
Max Act: 5.1637. Min Act: -0.1700
Data Index: 6390274 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1637. Min Range: -5.1637
Max Act: 5.1325. Min Act: -0.1700
Data Index: 1458081 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.9450. Min Act: -0.1700
Data Index: 3652541 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.9137. Min Act: -0.1700
Data Index: 7115225 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.9450. Min Act: -0.1700
Data Index: 4459044 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.9137. Min Act: -0.1700
Data Index: 3838022 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.8825. Min Act: -0.1700
Data Index: 107429 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.8825. Min Act: -0.1700
Data Index: 3836034 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.8825. Min Act: -0.1700
Data Index: 8070946 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.8512. Min Act: -0.1700
Data Index: 8088856 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.8825. Min Act: -0.1700
Data Index: 7656278 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.8512. Min Act: -0.1700
Data Index: 1893730 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.8512. Min Act: -0.1700
Data Index: 1860437 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.8200. Min Act: -0.1700
Data Index: 5627042 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.8200. Min Act: -0.1700
Data Index: 8255350 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.7887. Min Act: -0.1700
Data Index: 1952338 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.7887. Min Act: -0.1700
Data Index: 5819198 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.7887. Min Act: -0.1700
Data Index: 569419 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.7887. Min Act: -0.1700
Data Index: 2131198 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.8200. Min Act: -0.1700
Data Index: 5184603 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19