Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3642 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1759. Min Range: -5.1759
Max Act: 5.1759. Min Act: -0.1700
Data Index: 2079287 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1759. Min Range: -5.1759
Max Act: 5.0821. Min Act: -0.1700
Data Index: 7857334 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1759. Min Range: -5.1759
Max Act: 5.1134. Min Act: -0.1700
Data Index: 7241924 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1759. Min Range: -5.1759
Max Act: 5.0821. Min Act: -0.1700
Data Index: 3607267 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1759. Min Range: -5.1759
Max Act: 5.1134. Min Act: -0.1700
Data Index: 3802068 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1759. Min Range: -5.1759
Max Act: 5.0821. Min Act: -0.1700
Data Index: 4506148 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1759. Min Range: -5.1759
Max Act: 5.0509. Min Act: -0.1700
Data Index: 4011731 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1759. Min Range: -5.1759
Max Act: 5.0509. Min Act: -0.1700
Data Index: 4517224 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1759. Min Range: -5.1759
Max Act: 5.0821. Min Act: -0.1700
Data Index: 1239262 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1759. Min Range: -5.1759
Max Act: 5.0196. Min Act: -0.1700
Data Index: 1035889 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1759. Min Range: -5.1759
Max Act: 4.9571. Min Act: -0.1700
Data Index: 8195508 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1759. Min Range: -5.1759
Max Act: 4.9571. Min Act: -0.1700
Data Index: 5815197 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1759. Min Range: -5.1759
Max Act: 4.9571. Min Act: -0.1700
Data Index: 3643634 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1759. Min Range: -5.1759
Max Act: 4.9571. Min Act: -0.1700
Data Index: 1755675 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1759. Min Range: -5.1759
Max Act: 4.9259. Min Act: -0.1700
Data Index: 4117601 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1759. Min Range: -5.1759
Max Act: 4.9259. Min Act: -0.1700
Data Index: 1239263 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1759. Min Range: -5.1759
Max Act: 4.9259. Min Act: -0.1700
Data Index: 4162614 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1759. Min Range: -5.1759
Max Act: 4.8946. Min Act: -0.1700
Data Index: 7757389 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1759. Min Range: -5.1759
Max Act: 4.8946. Min Act: -0.1700
Data Index: 7285255 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1759. Min Range: -5.1759
Max Act: 4.8946. Min Act: -0.1700
Data Index: 4936958 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19