Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3306 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9909. Min Range: -1.9909
Max Act: 1.9909. Min Act: -0.1700
Data Index: 8759775 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9909. Min Range: -1.9909
Max Act: 1.9060. Min Act: -0.1700
Data Index: 4074662 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9909. Min Range: -1.9909
Max Act: 1.9060. Min Act: -0.1697
Data Index: 191299 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9909. Min Range: -1.9909
Max Act: 1.8889. Min Act: -0.1700
Data Index: 5427188 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9909. Min Range: -1.9909
Max Act: 1.8889. Min Act: -0.1560
Data Index: 7064299 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9909. Min Range: -1.9909
Max Act: 1.8718. Min Act: -0.1700
Data Index: 502522 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9909. Min Range: -1.9909
Max Act: 1.8718. Min Act: -0.1700
Data Index: 5210696 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9909. Min Range: -1.9909
Max Act: 1.8547. Min Act: -0.1700
Data Index: 748803 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9909. Min Range: -1.9909
Max Act: 1.8547. Min Act: -0.1700
Data Index: 2487818 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9909. Min Range: -1.9909
Max Act: 1.8461. Min Act: -0.1700
Data Index: 2827465 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9909. Min Range: -1.9909
Max Act: 1.8461. Min Act: -0.1697
Data Index: 1949453 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9909. Min Range: -1.9909
Max Act: 1.8290. Min Act: -0.1700
Data Index: 251572 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9909. Min Range: -1.9909
Max Act: 1.8290. Min Act: -0.1700
Data Index: 6106254 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9909. Min Range: -1.9909
Max Act: 1.8290. Min Act: -0.1700
Data Index: 4337167 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9909. Min Range: -1.9909
Max Act: 1.8204. Min Act: -0.1693
Data Index: 2100440 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9909. Min Range: -1.9909
Max Act: 1.8118. Min Act: -0.1695
Data Index: 5830083 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9909. Min Range: -1.9909
Max Act: 1.8118. Min Act: -0.1698
Data Index: 6252343 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9909. Min Range: -1.9909
Max Act: 1.8032. Min Act: -0.1700
Data Index: 910364 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9909. Min Range: -1.9909
Max Act: 1.7946. Min Act: -0.1700
Data Index: 3889602 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9909. Min Range: -1.9909
Max Act: 1.8032. Min Act: -0.1700
Data Index: 3444865 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19