Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2784 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2562. Min Range: -6.2562
Max Act: 6.2562. Min Act: -0.1700
Data Index: 4691270 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2562. Min Range: -6.2562
Max Act: 6.2562. Min Act: -0.1700
Data Index: 5401422 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2562. Min Range: -6.2562
Max Act: 6.2562. Min Act: -0.1700
Data Index: 5806307 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2562. Min Range: -6.2562
Max Act: 6.1625. Min Act: -0.1700
Data Index: 3088406 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2562. Min Range: -6.2562
Max Act: 6.1937. Min Act: -0.1700
Data Index: 2895576 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2562. Min Range: -6.2562
Max Act: 6.2250. Min Act: -0.1700
Data Index: 3517387 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2562. Min Range: -6.2562
Max Act: 6.1625. Min Act: -0.1700
Data Index: 8638167 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2562. Min Range: -6.2562
Max Act: 6.1312. Min Act: -0.1700
Data Index: 4969501 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2562. Min Range: -6.2562
Max Act: 6.1625. Min Act: -0.1700
Data Index: 7041720 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2562. Min Range: -6.2562
Max Act: 6.1625. Min Act: -0.1700
Data Index: 785643 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2562. Min Range: -6.2562
Max Act: 6.1937. Min Act: -0.1700
Data Index: 2276086 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2562. Min Range: -6.2562
Max Act: 6.1937. Min Act: -0.1700
Data Index: 5104029 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2562. Min Range: -6.2562
Max Act: 6.1625. Min Act: -0.1700
Data Index: 3802335 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2562. Min Range: -6.2562
Max Act: 6.1312. Min Act: -0.1700
Data Index: 8403811 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2562. Min Range: -6.2562
Max Act: 6.1000. Min Act: -0.1700
Data Index: 4656908 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2562. Min Range: -6.2562
Max Act: 6.1312. Min Act: -0.1700
Data Index: 2502183 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2562. Min Range: -6.2562
Max Act: 6.1312. Min Act: -0.1700
Data Index: 1453051 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2562. Min Range: -6.2562
Max Act: 6.1312. Min Act: -0.1700
Data Index: 5222154 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2562. Min Range: -6.2562
Max Act: 6.1312. Min Act: -0.1700
Data Index: 4827076 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2562. Min Range: -6.2562
Max Act: 6.1000. Min Act: -0.1700
Data Index: 40888 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19