Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2818 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9221. Min Range: -5.9221
Max Act: 5.9221. Min Act: -0.1700
Data Index: 2070124 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9221. Min Range: -5.9221
Max Act: 5.8596. Min Act: -0.1700
Data Index: 7528270 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9221. Min Range: -5.9221
Max Act: 5.8596. Min Act: -0.1700
Data Index: 3664776 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9221. Min Range: -5.9221
Max Act: 5.8596. Min Act: -0.1700
Data Index: 5533061 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9221. Min Range: -5.9221
Max Act: 5.8283. Min Act: -0.1700
Data Index: 1335370 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9221. Min Range: -5.9221
Max Act: 5.8283. Min Act: -0.1700
Data Index: 7494778 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9221. Min Range: -5.9221
Max Act: 5.8283. Min Act: -0.1700
Data Index: 5555374 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9221. Min Range: -5.9221
Max Act: 5.7971. Min Act: -0.1700
Data Index: 7880456 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9221. Min Range: -5.9221
Max Act: 5.7658. Min Act: -0.1700
Data Index: 8556271 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9221. Min Range: -5.9221
Max Act: 5.7658. Min Act: -0.1700
Data Index: 7832620 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9221. Min Range: -5.9221
Max Act: 5.7658. Min Act: -0.1700
Data Index: 5285911 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9221. Min Range: -5.9221
Max Act: 5.7658. Min Act: -0.1700
Data Index: 1811177 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9221. Min Range: -5.9221
Max Act: 5.7658. Min Act: -0.1700
Data Index: 8792047 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9221. Min Range: -5.9221
Max Act: 5.7033. Min Act: -0.1700
Data Index: 5805233 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9221. Min Range: -5.9221
Max Act: 5.6721. Min Act: -0.1700
Data Index: 5533059 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9221. Min Range: -5.9221
Max Act: 5.7033. Min Act: -0.1700
Data Index: 4590495 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9221. Min Range: -5.9221
Max Act: 5.7033. Min Act: -0.1700
Data Index: 8046569 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9221. Min Range: -5.9221
Max Act: 5.6721. Min Act: -0.1700
Data Index: 7750586 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9221. Min Range: -5.9221
Max Act: 5.6408. Min Act: -0.1700
Data Index: 3296827 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9221. Min Range: -5.9221
Max Act: 5.6408. Min Act: -0.1700
Data Index: 5043556 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19