Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2024 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0214. Min Range: -5.0214
Max Act: 5.0214. Min Act: -0.1700
Data Index: 5724210 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.9589. Min Act: -0.1700
Data Index: 8350539 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.9589. Min Act: -0.1700
Data Index: 3479443 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.9901. Min Act: -0.1700
Data Index: 2430726 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.9276. Min Act: -0.1700
Data Index: 6290146 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.9276. Min Act: -0.1700
Data Index: 7251195 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.9589. Min Act: -0.1700
Data Index: 7365904 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.9589. Min Act: -0.1700
Data Index: 4910757 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.8964. Min Act: -0.1700
Data Index: 1260564 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.8964. Min Act: -0.1700
Data Index: 65185 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.8964. Min Act: -0.1700
Data Index: 5425039 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.8651. Min Act: -0.1700
Data Index: 424162 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.8339. Min Act: -0.1700
Data Index: 5426840 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.8651. Min Act: -0.1700
Data Index: 4565577 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.8651. Min Act: -0.1700
Data Index: 3872976 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.8651. Min Act: -0.1700
Data Index: 5100836 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.8339. Min Act: -0.1700
Data Index: 3830915 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.8026. Min Act: -0.1700
Data Index: 5924310 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.8339. Min Act: -0.1700
Data Index: 1163388 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.8026. Min Act: -0.1700
Data Index: 1342576 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19