Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1223 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1108. Min Range: -7.1108
Max Act: 7.0795. Min Act: -0.1700
Data Index: 3252424 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1108. Min Range: -7.1108
Max Act: 7.1108. Min Act: -0.1700
Data Index: 641560 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1108. Min Range: -7.1108
Max Act: 6.9858. Min Act: -0.1700
Data Index: 2971680 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1108. Min Range: -7.1108
Max Act: 6.8920. Min Act: -0.1700
Data Index: 3319181 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1108. Min Range: -7.1108
Max Act: 6.8920. Min Act: -0.1700
Data Index: 6617440 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1108. Min Range: -7.1108
Max Act: 6.7983. Min Act: -0.1700
Data Index: 1995648 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1108. Min Range: -7.1108
Max Act: 6.7045. Min Act: -0.1700
Data Index: 7327088 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1108. Min Range: -7.1108
Max Act: 6.7045. Min Act: -0.1700
Data Index: 987833 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1108. Min Range: -7.1108
Max Act: 6.7045. Min Act: -0.1700
Data Index: 2895731 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1108. Min Range: -7.1108
Max Act: 6.6420. Min Act: -0.1700
Data Index: 1585905 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1108. Min Range: -7.1108
Max Act: 6.6108. Min Act: -0.1700
Data Index: 928023 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1108. Min Range: -7.1108
Max Act: 6.6420. Min Act: -0.1700
Data Index: 2379952 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1108. Min Range: -7.1108
Max Act: 6.5483. Min Act: -0.1700
Data Index: 5663580 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1108. Min Range: -7.1108
Max Act: 6.5483. Min Act: -0.1700
Data Index: 3841197 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1108. Min Range: -7.1108
Max Act: 6.5483. Min Act: -0.1700
Data Index: 4825076 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1108. Min Range: -7.1108
Max Act: 6.5483. Min Act: -0.1700
Data Index: 6459951 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1108. Min Range: -7.1108
Max Act: 6.5483. Min Act: -0.1700
Data Index: 1076869 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1108. Min Range: -7.1108
Max Act: 6.4858. Min Act: -0.1700
Data Index: 7125655 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1108. Min Range: -7.1108
Max Act: 6.5170. Min Act: -0.1700
Data Index: 1048956 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1108. Min Range: -7.1108
Max Act: 6.5170. Min Act: -0.1700
Data Index: 32304 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19