Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2833 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0615. Min Range: -5.0615
Max Act: 5.0615. Min Act: -0.1700
Data Index: 5838258 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0615. Min Range: -5.0615
Max Act: 5.0303. Min Act: -0.1700
Data Index: 5178757 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0615. Min Range: -5.0615
Max Act: 5.0303. Min Act: -0.1700
Data Index: 8310837 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0615. Min Range: -5.0615
Max Act: 4.9990. Min Act: -0.1700
Data Index: 6066326 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0615. Min Range: -5.0615
Max Act: 4.9678. Min Act: -0.1700
Data Index: 1529399 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0615. Min Range: -5.0615
Max Act: 4.9678. Min Act: -0.1700
Data Index: 8560825 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0615. Min Range: -5.0615
Max Act: 4.9678. Min Act: -0.1700
Data Index: 5090476 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0615. Min Range: -5.0615
Max Act: 4.9678. Min Act: -0.1700
Data Index: 1927001 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0615. Min Range: -5.0615
Max Act: 4.9365. Min Act: -0.1700
Data Index: 8802673 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0615. Min Range: -5.0615
Max Act: 4.8740. Min Act: -0.1700
Data Index: 3989638 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0615. Min Range: -5.0615
Max Act: 4.8740. Min Act: -0.1700
Data Index: 5918444 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0615. Min Range: -5.0615
Max Act: 4.8428. Min Act: -0.1700
Data Index: 4160258 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0615. Min Range: -5.0615
Max Act: 4.8115. Min Act: -0.1700
Data Index: 789517 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0615. Min Range: -5.0615
Max Act: 4.8115. Min Act: -0.1700
Data Index: 5964651 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0615. Min Range: -5.0615
Max Act: 4.8115. Min Act: -0.1700
Data Index: 3179029 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0615. Min Range: -5.0615
Max Act: 4.8115. Min Act: -0.1700
Data Index: 7481257 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0615. Min Range: -5.0615
Max Act: 4.7803. Min Act: -0.1700
Data Index: 2038649 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0615. Min Range: -5.0615
Max Act: 4.7803. Min Act: -0.1700
Data Index: 7044423 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0615. Min Range: -5.0615
Max Act: 4.7803. Min Act: -0.1700
Data Index: 7504960 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0615. Min Range: -5.0615
Max Act: 4.7490. Min Act: -0.1700
Data Index: 4597759 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19