Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2774 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2180. Min Range: -7.2180
Max Act: 7.2180. Min Act: -0.1700
Data Index: 1249391 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2180. Min Range: -7.2180
Max Act: 7.0305. Min Act: -0.1700
Data Index: 1249395 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2180. Min Range: -7.2180
Max Act: 6.9368. Min Act: -0.1700
Data Index: 1249390 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2180. Min Range: -7.2180
Max Act: 6.9993. Min Act: -0.1700
Data Index: 1249394 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2180. Min Range: -7.2180
Max Act: 6.9368. Min Act: -0.1700
Data Index: 1249396 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2180. Min Range: -7.2180
Max Act: 6.9055. Min Act: -0.1700
Data Index: 3026789 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2180. Min Range: -7.2180
Max Act: 6.8430. Min Act: -0.1700
Data Index: 1084324 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2180. Min Range: -7.2180
Max Act: 6.8118. Min Act: -0.1700
Data Index: 1249388 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2180. Min Range: -7.2180
Max Act: 6.7805. Min Act: -0.1700
Data Index: 7803797 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2180. Min Range: -7.2180
Max Act: 6.8118. Min Act: -0.1700
Data Index: 1249387 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2180. Min Range: -7.2180
Max Act: 6.7493. Min Act: -0.1700
Data Index: 3026796 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2180. Min Range: -7.2180
Max Act: 6.6868. Min Act: -0.1700
Data Index: 1249389 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2180. Min Range: -7.2180
Max Act: 6.6555. Min Act: -0.1700
Data Index: 3026793 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2180. Min Range: -7.2180
Max Act: 6.7180. Min Act: -0.1700
Data Index: 1249383 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2180. Min Range: -7.2180
Max Act: 6.6555. Min Act: -0.1700
Data Index: 581363 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2180. Min Range: -7.2180
Max Act: 6.6555. Min Act: -0.1700
Data Index: 1249386 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2180. Min Range: -7.2180
Max Act: 6.6243. Min Act: -0.1700
Data Index: 833329 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2180. Min Range: -7.2180
Max Act: 6.6243. Min Act: -0.1700
Data Index: 3026794 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2180. Min Range: -7.2180
Max Act: 6.6555. Min Act: -0.1700
Data Index: 19097 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2180. Min Range: -7.2180
Max Act: 6.5930. Min Act: -0.1700
Data Index: 7480118 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19