Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 851 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0470. Min Range: -4.0470
Max Act: 4.0470. Min Act: -0.1700
Data Index: 2995239 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0470. Min Range: -4.0470
Max Act: 3.9845. Min Act: -0.1700
Data Index: 4609441 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0470. Min Range: -4.0470
Max Act: 3.9845. Min Act: -0.1700
Data Index: 4167948 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0470. Min Range: -4.0470
Max Act: 3.9845. Min Act: -0.1700
Data Index: 6191790 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0470. Min Range: -4.0470
Max Act: 3.9845. Min Act: -0.1700
Data Index: 760205 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0470. Min Range: -4.0470
Max Act: 3.9532. Min Act: -0.1700
Data Index: 7910297 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0470. Min Range: -4.0470
Max Act: 3.9532. Min Act: -0.1700
Data Index: 7542092 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0470. Min Range: -4.0470
Max Act: 3.9532. Min Act: -0.1700
Data Index: 3190206 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0470. Min Range: -4.0470
Max Act: 3.9532. Min Act: -0.1700
Data Index: 3490695 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0470. Min Range: -4.0470
Max Act: 3.9220. Min Act: -0.1700
Data Index: 140455 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0470. Min Range: -4.0470
Max Act: 3.8907. Min Act: -0.1700
Data Index: 1152132 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0470. Min Range: -4.0470
Max Act: 3.8907. Min Act: -0.1700
Data Index: 266386 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0470. Min Range: -4.0470
Max Act: 3.8594. Min Act: -0.1700
Data Index: 7270571 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0470. Min Range: -4.0470
Max Act: 3.8438. Min Act: -0.1700
Data Index: 3489389 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0470. Min Range: -4.0470
Max Act: 3.8594. Min Act: -0.1700
Data Index: 7733732 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0470. Min Range: -4.0470
Max Act: 3.8438. Min Act: -0.1700
Data Index: 1753791 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0470. Min Range: -4.0470
Max Act: 3.8282. Min Act: -0.1700
Data Index: 4980211 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0470. Min Range: -4.0470
Max Act: 3.8282. Min Act: -0.1700
Data Index: 4364783 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0470. Min Range: -4.0470
Max Act: 3.8282. Min Act: -0.1700
Data Index: 6699476 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0470. Min Range: -4.0470
Max Act: 3.8125. Min Act: -0.1700
Data Index: 2183983 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #19