Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2464 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1345. Min Range: -2.1345
Max Act: 2.1345. Min Act: -0.1700
Data Index: 915997 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1345. Min Range: -2.1345
Max Act: 2.1178. Min Act: -0.1700
Data Index: 8777058 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1345. Min Range: -2.1345
Max Act: 2.0675. Min Act: -0.1700
Data Index: 6270826 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1345. Min Range: -2.1345
Max Act: 2.0675. Min Act: -0.1700
Data Index: 4895032 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1345. Min Range: -2.1345
Max Act: 2.0507. Min Act: -0.1700
Data Index: 2787136 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1345. Min Range: -2.1345
Max Act: 2.0507. Min Act: -0.1700
Data Index: 3079866 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1345. Min Range: -2.1345
Max Act: 2.0507. Min Act: -0.1700
Data Index: 1731264 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1345. Min Range: -2.1345
Max Act: 2.0170. Min Act: -0.1700
Data Index: 4848485 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1345. Min Range: -2.1345
Max Act: 2.0339. Min Act: -0.1700
Data Index: 8140947 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1345. Min Range: -2.1345
Max Act: 2.0001. Min Act: -0.1700
Data Index: 8181648 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1345. Min Range: -2.1345
Max Act: 2.0170. Min Act: -0.1700
Data Index: 3425293 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1345. Min Range: -2.1345
Max Act: 2.0170. Min Act: -0.1700
Data Index: 337976 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1345. Min Range: -2.1345
Max Act: 2.0001. Min Act: -0.1700
Data Index: 1477597 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1345. Min Range: -2.1345
Max Act: 1.9832. Min Act: -0.1700
Data Index: 2724924 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1345. Min Range: -2.1345
Max Act: 1.9832. Min Act: -0.1700
Data Index: 4971971 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1345. Min Range: -2.1345
Max Act: 1.9663. Min Act: -0.1700
Data Index: 960317 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1345. Min Range: -2.1345
Max Act: 1.9493. Min Act: -0.1700
Data Index: 4373065 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1345. Min Range: -2.1345
Max Act: 1.9663. Min Act: -0.1700
Data Index: 1477602 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1345. Min Range: -2.1345
Max Act: 1.9663. Min Act: -0.1700
Data Index: 2041867 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1345. Min Range: -2.1345
Max Act: 1.9663. Min Act: -0.1700
Data Index: 6982390 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19