Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 659 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0030. Min Range: -7.0030
Max Act: 7.0030. Min Act: -0.1700
Data Index: 8179640 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0030. Min Range: -7.0030
Max Act: 7.0030. Min Act: -0.1700
Data Index: 109975 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0030. Min Range: -7.0030
Max Act: 6.9405. Min Act: -0.1700
Data Index: 109960 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0030. Min Range: -7.0030
Max Act: 6.9405. Min Act: -0.1700
Data Index: 4899678 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0030. Min Range: -7.0030
Max Act: 6.9405. Min Act: -0.1700
Data Index: 4132402 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0030. Min Range: -7.0030
Max Act: 6.9405. Min Act: -0.1700
Data Index: 1768162 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0030. Min Range: -7.0030
Max Act: 6.9405. Min Act: -0.1700
Data Index: 2046513 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0030. Min Range: -7.0030
Max Act: 6.8780. Min Act: -0.1700
Data Index: 6307837 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0030. Min Range: -7.0030
Max Act: 6.8780. Min Act: -0.1700
Data Index: 7878502 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0030. Min Range: -7.0030
Max Act: 6.8780. Min Act: -0.1700
Data Index: 2322818 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0030. Min Range: -7.0030
Max Act: 6.8780. Min Act: -0.1700
Data Index: 6815580 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0030. Min Range: -7.0030
Max Act: 6.8780. Min Act: -0.1700
Data Index: 5811219 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0030. Min Range: -7.0030
Max Act: 6.8155. Min Act: -0.1700
Data Index: 6999798 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0030. Min Range: -7.0030
Max Act: 6.8155. Min Act: -0.1700
Data Index: 4293758 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0030. Min Range: -7.0030
Max Act: 6.8155. Min Act: -0.1700
Data Index: 6769872 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0030. Min Range: -7.0030
Max Act: 6.8155. Min Act: -0.1700
Data Index: 6528647 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0030. Min Range: -7.0030
Max Act: 6.8155. Min Act: -0.1700
Data Index: 8446313 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0030. Min Range: -7.0030
Max Act: 6.8155. Min Act: -0.1700
Data Index: 8558223 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0030. Min Range: -7.0030
Max Act: 6.8155. Min Act: -0.1700
Data Index: 6331180 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0030. Min Range: -7.0030
Max Act: 6.7843. Min Act: -0.1700
Data Index: 109965 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #19