Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3145 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4730. Min Range: -7.4730
Max Act: 7.4730. Min Act: -0.1700
Data Index: 3954251 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4730. Min Range: -7.4730
Max Act: 7.4730. Min Act: -0.1700
Data Index: 2202332 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4730. Min Range: -7.4730
Max Act: 7.4105. Min Act: -0.1700
Data Index: 6642485 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4730. Min Range: -7.4730
Max Act: 7.4105. Min Act: -0.1700
Data Index: 5022367 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4730. Min Range: -7.4730
Max Act: 7.3167. Min Act: -0.1700
Data Index: 1798610 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4730. Min Range: -7.4730
Max Act: 7.3167. Min Act: -0.1700
Data Index: 2338723 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4730. Min Range: -7.4730
Max Act: 7.3167. Min Act: -0.1700
Data Index: 6424951 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4730. Min Range: -7.4730
Max Act: 7.2542. Min Act: -0.1700
Data Index: 1467939 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4730. Min Range: -7.4730
Max Act: 7.2230. Min Act: -0.1700
Data Index: 4069524 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4730. Min Range: -7.4730
Max Act: 7.2542. Min Act: -0.1700
Data Index: 1848009 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4730. Min Range: -7.4730
Max Act: 7.1917. Min Act: -0.1700
Data Index: 6180732 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4730. Min Range: -7.4730
Max Act: 7.1917. Min Act: -0.1700
Data Index: 4012992 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4730. Min Range: -7.4730
Max Act: 7.1917. Min Act: -0.1700
Data Index: 2768849 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4730. Min Range: -7.4730
Max Act: 7.1605. Min Act: -0.1700
Data Index: 98010 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4730. Min Range: -7.4730
Max Act: 7.1605. Min Act: -0.1700
Data Index: 6835173 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4730. Min Range: -7.4730
Max Act: 7.1605. Min Act: -0.1700
Data Index: 7121852 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4730. Min Range: -7.4730
Max Act: 7.0980. Min Act: -0.1700
Data Index: 4815597 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4730. Min Range: -7.4730
Max Act: 7.0980. Min Act: -0.1700
Data Index: 7539535 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4730. Min Range: -7.4730
Max Act: 7.1292. Min Act: -0.1700
Data Index: 1530015 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4730. Min Range: -7.4730
Max Act: 7.0980. Min Act: -0.1700
Data Index: 1211736 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19