Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1461 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.5054. Min Act: -0.1700
Data Index: 4961312 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.4429. Min Act: -0.1700
Data Index: 539992 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.3491. Min Act: -0.1700
Data Index: 6308867 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.2866. Min Act: -0.1700
Data Index: 7370737 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.2866. Min Act: -0.1700
Data Index: 403831 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.2866. Min Act: -0.1700
Data Index: 3058634 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.2866. Min Act: -0.1700
Data Index: 1180215 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.2866. Min Act: -0.1700
Data Index: 6691949 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.2866. Min Act: -0.1700
Data Index: 3134431 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.2866. Min Act: -0.1700
Data Index: 1077231 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.2866. Min Act: -0.1700
Data Index: 3022977 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.2866. Min Act: -0.1700
Data Index: 1426922 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.2866. Min Act: -0.1700
Data Index: 7483647 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.2866. Min Act: -0.1700
Data Index: 4607325 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.2866. Min Act: -0.1700
Data Index: 4582510 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.2866. Min Act: -0.1700
Data Index: 1854004 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.2866. Min Act: -0.1700
Data Index: 4933651 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.2866. Min Act: -0.1700
Data Index: 3894747 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.2866. Min Act: -0.1700
Data Index: 7290132 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.2866. Min Act: -0.1700
Data Index: 4228823 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19