Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2107 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 0.9122. Min Range: -0.9122
Max Act: 0.9122. Min Act: -0.1700
Data Index: 4939262 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9122. Min Range: -0.9122
Max Act: 0.9122. Min Act: -0.1700
Data Index: 5626779 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9122. Min Range: -0.9122
Max Act: 0.9122. Min Act: -0.1700
Data Index: 965964 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9122. Min Range: -0.9122
Max Act: 0.9122. Min Act: -0.1700
Data Index: 6989442 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9122. Min Range: -0.9122
Max Act: 0.9037. Min Act: -0.1700
Data Index: 3882630 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9122. Min Range: -0.9122
Max Act: 0.8951. Min Act: -0.1700
Data Index: 2133758 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9122. Min Range: -0.9122
Max Act: 0.8994. Min Act: -0.1700
Data Index: 7377361 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9122. Min Range: -0.9122
Max Act: 0.8994. Min Act: -0.1700
Data Index: 704279 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9122. Min Range: -0.9122
Max Act: 0.8994. Min Act: -0.1700
Data Index: 8718797 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9122. Min Range: -0.9122
Max Act: 0.8908. Min Act: -0.1700
Data Index: 5627492 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9122. Min Range: -0.9122
Max Act: 0.8908. Min Act: -0.1700
Data Index: 3279980 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9122. Min Range: -0.9122
Max Act: 0.8951. Min Act: -0.1700
Data Index: 603036 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9122. Min Range: -0.9122
Max Act: 0.8908. Min Act: -0.1700
Data Index: 8179060 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9122. Min Range: -0.9122
Max Act: 0.8908. Min Act: -0.1700
Data Index: 7527953 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9122. Min Range: -0.9122
Max Act: 0.8908. Min Act: -0.1700
Data Index: 6073255 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9122. Min Range: -0.9122
Max Act: 0.8780. Min Act: -0.1700
Data Index: 6447902 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9122. Min Range: -0.9122
Max Act: 0.8866. Min Act: -0.1700
Data Index: 955390 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9122. Min Range: -0.9122
Max Act: 0.8780. Min Act: -0.1700
Data Index: 4074383 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9122. Min Range: -0.9122
Max Act: 0.8866. Min Act: -0.1700
Data Index: 2219648 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9122. Min Range: -0.9122
Max Act: 0.8908. Min Act: -0.1700
Data Index: 6462457 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19