Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 474 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0969. Min Range: -4.0969
Max Act: 4.0969. Min Act: -0.1700
Data Index: 1327182 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0969. Min Range: -4.0969
Max Act: 3.9719. Min Act: -0.1700
Data Index: 2903699 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0969. Min Range: -4.0969
Max Act: 3.9719. Min Act: -0.1700
Data Index: 7423534 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0969. Min Range: -4.0969
Max Act: 3.9093. Min Act: -0.1700
Data Index: 4506524 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0969. Min Range: -4.0969
Max Act: 3.9093. Min Act: -0.1700
Data Index: 38039 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0969. Min Range: -4.0969
Max Act: 3.8781. Min Act: -0.1700
Data Index: 1466178 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0969. Min Range: -4.0969
Max Act: 3.8781. Min Act: -0.1700
Data Index: 4846634 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0969. Min Range: -4.0969
Max Act: 3.8781. Min Act: -0.1700
Data Index: 1466162 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0969. Min Range: -4.0969
Max Act: 3.8468. Min Act: -0.1700
Data Index: 1974450 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0969. Min Range: -4.0969
Max Act: 3.8155. Min Act: -0.1700
Data Index: 374916 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0969. Min Range: -4.0969
Max Act: 3.8155. Min Act: -0.1700
Data Index: 4682261 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0969. Min Range: -4.0969
Max Act: 3.8155. Min Act: -0.1700
Data Index: 7353517 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0969. Min Range: -4.0969
Max Act: 3.8155. Min Act: -0.1700
Data Index: 374849 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0969. Min Range: -4.0969
Max Act: 3.8155. Min Act: -0.1700
Data Index: 3574082 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0969. Min Range: -4.0969
Max Act: 3.7843. Min Act: -0.1700
Data Index: 2778329 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0969. Min Range: -4.0969
Max Act: 3.8155. Min Act: -0.1700
Data Index: 8545641 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0969. Min Range: -4.0969
Max Act: 3.7843. Min Act: -0.1700
Data Index: 5585378 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0969. Min Range: -4.0969
Max Act: 3.7843. Min Act: -0.1700
Data Index: 2366210 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0969. Min Range: -4.0969
Max Act: 3.7530. Min Act: -0.1700
Data Index: 1466174 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0969. Min Range: -4.0969
Max Act: 3.6904. Min Act: -0.1700
Data Index: 4616667 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19