Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3014 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7028. Min Range: -4.7028
Max Act: 4.7028. Min Act: -0.1700
Data Index: 1305986 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7028. Min Range: -4.7028
Max Act: 4.7028. Min Act: -0.1700
Data Index: 76163 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7028. Min Range: -4.7028
Max Act: 4.6716. Min Act: -0.1700
Data Index: 6965983 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7028. Min Range: -4.7028
Max Act: 4.6716. Min Act: -0.1700
Data Index: 7527726 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7028. Min Range: -4.7028
Max Act: 4.6403. Min Act: -0.1700
Data Index: 4426340 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7028. Min Range: -4.7028
Max Act: 4.6403. Min Act: -0.1700
Data Index: 3417905 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7028. Min Range: -4.7028
Max Act: 4.6403. Min Act: -0.1700
Data Index: 6399380 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7028. Min Range: -4.7028
Max Act: 4.6091. Min Act: -0.1700
Data Index: 6436830 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7028. Min Range: -4.7028
Max Act: 4.5778. Min Act: -0.1700
Data Index: 6334012 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7028. Min Range: -4.7028
Max Act: 4.6091. Min Act: -0.1700
Data Index: 3010523 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7028. Min Range: -4.7028
Max Act: 4.6403. Min Act: -0.1700
Data Index: 6372388 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7028. Min Range: -4.7028
Max Act: 4.5466. Min Act: -0.1700
Data Index: 423932 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7028. Min Range: -4.7028
Max Act: 4.6091. Min Act: -0.1700
Data Index: 4000985 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7028. Min Range: -4.7028
Max Act: 4.6091. Min Act: -0.1700
Data Index: 3622796 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7028. Min Range: -4.7028
Max Act: 4.5466. Min Act: -0.1700
Data Index: 631043 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7028. Min Range: -4.7028
Max Act: 4.5466. Min Act: -0.1700
Data Index: 1588466 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7028. Min Range: -4.7028
Max Act: 4.5778. Min Act: -0.1700
Data Index: 321492 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7028. Min Range: -4.7028
Max Act: 4.5778. Min Act: -0.1700
Data Index: 3003432 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7028. Min Range: -4.7028
Max Act: 4.5778. Min Act: -0.1700
Data Index: 874522 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7028. Min Range: -4.7028
Max Act: 4.5778. Min Act: -0.1700
Data Index: 5369466 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19