Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3974 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.2922. Min Range: -1.2922
Max Act: 1.2922. Min Act: -0.1700
Data Index: 5438928 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2922. Min Range: -1.2922
Max Act: 1.2569. Min Act: -0.1700
Data Index: 3893389 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2922. Min Range: -1.2922
Max Act: 1.2393. Min Act: -0.1700
Data Index: 671061 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2922. Min Range: -1.2922
Max Act: 1.2217. Min Act: -0.1700
Data Index: 5438927 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2922. Min Range: -1.2922
Max Act: 1.2217. Min Act: -0.1698
Data Index: 7182328 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2922. Min Range: -1.2922
Max Act: 1.2040. Min Act: -0.1699
Data Index: 3747777 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2922. Min Range: -1.2922
Max Act: 1.1864. Min Act: -0.1699
Data Index: 5154699 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2922. Min Range: -1.2922
Max Act: 1.1864. Min Act: -0.1700
Data Index: 6646366 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2922. Min Range: -1.2922
Max Act: 1.1688. Min Act: -0.1700
Data Index: 2535138 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2922. Min Range: -1.2922
Max Act: 1.1513. Min Act: -0.1700
Data Index: 8499544 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2922. Min Range: -1.2922
Max Act: 1.1513. Min Act: -0.1700
Data Index: 6207866 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2922. Min Range: -1.2922
Max Act: 1.1337. Min Act: -0.1700
Data Index: 2446775 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2922. Min Range: -1.2922
Max Act: 1.1161. Min Act: -0.1700
Data Index: 8564579 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2922. Min Range: -1.2922
Max Act: 1.1161. Min Act: -0.1700
Data Index: 118417 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2922. Min Range: -1.2922
Max Act: 1.0811. Min Act: -0.1698
Data Index: 200606 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2922. Min Range: -1.2922
Max Act: 1.1161. Min Act: -0.1700
Data Index: 837351 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2922. Min Range: -1.2922
Max Act: 1.0811. Min Act: -0.1700
Data Index: 3293055 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2922. Min Range: -1.2922
Max Act: 1.0636. Min Act: -0.1700
Data Index: 8536196 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2922. Min Range: -1.2922
Max Act: 1.0811. Min Act: -0.1700
Data Index: 2539079 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2922. Min Range: -1.2922
Max Act: 1.0811. Min Act: -0.1700
Data Index: 3107222 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19