Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2726 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4777. Min Range: -6.4777
Max Act: 6.4777. Min Act: -0.1700
Data Index: 4153082 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4777. Min Range: -6.4777
Max Act: 6.4464. Min Act: -0.1700
Data Index: 4491397 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4777. Min Range: -6.4777
Max Act: 6.4464. Min Act: -0.1700
Data Index: 7444933 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4777. Min Range: -6.4777
Max Act: 6.4777. Min Act: -0.1700
Data Index: 2298196 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4777. Min Range: -6.4777
Max Act: 6.3839. Min Act: -0.1700
Data Index: 4221422 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4777. Min Range: -6.4777
Max Act: 6.2902. Min Act: -0.1700
Data Index: 7005307 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4777. Min Range: -6.4777
Max Act: 6.2902. Min Act: -0.1700
Data Index: 3748956 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4777. Min Range: -6.4777
Max Act: 6.2589. Min Act: -0.1700
Data Index: 2700945 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4777. Min Range: -6.4777
Max Act: 6.1964. Min Act: -0.1700
Data Index: 638571 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4777. Min Range: -6.4777
Max Act: 6.1964. Min Act: -0.1700
Data Index: 4754620 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4777. Min Range: -6.4777
Max Act: 6.1652. Min Act: -0.1700
Data Index: 638570 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4777. Min Range: -6.4777
Max Act: 6.1652. Min Act: -0.1700
Data Index: 4255941 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4777. Min Range: -6.4777
Max Act: 6.1339. Min Act: -0.1700
Data Index: 1860138 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4777. Min Range: -6.4777
Max Act: 6.1027. Min Act: -0.1700
Data Index: 638569 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4777. Min Range: -6.4777
Max Act: 6.1339. Min Act: -0.1700
Data Index: 638567 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4777. Min Range: -6.4777
Max Act: 6.1027. Min Act: -0.1700
Data Index: 1253245 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4777. Min Range: -6.4777
Max Act: 6.1339. Min Act: -0.1700
Data Index: 6139793 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4777. Min Range: -6.4777
Max Act: 6.1027. Min Act: -0.1700
Data Index: 6584083 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4777. Min Range: -6.4777
Max Act: 6.1027. Min Act: -0.1700
Data Index: 6271648 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4777. Min Range: -6.4777
Max Act: 6.0714. Min Act: -0.1700
Data Index: 5902981 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19