Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3142 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0731. Min Range: -3.0731
Max Act: 3.0731. Min Act: -0.1700
Data Index: 855867 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0731. Min Range: -3.0731
Max Act: 2.9309. Min Act: -0.1700
Data Index: 2315919 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0731. Min Range: -3.0731
Max Act: 2.9309. Min Act: -0.1700
Data Index: 5913079 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0731. Min Range: -3.0731
Max Act: 2.8992. Min Act: -0.1700
Data Index: 7289948 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0731. Min Range: -3.0731
Max Act: 2.8516. Min Act: -0.1700
Data Index: 951347 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0731. Min Range: -3.0731
Max Act: 2.8357. Min Act: -0.1700
Data Index: 7293692 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0731. Min Range: -3.0731
Max Act: 2.8039. Min Act: -0.1700
Data Index: 3268726 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0731. Min Range: -3.0731
Max Act: 2.8039. Min Act: -0.1700
Data Index: 4884293 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0731. Min Range: -3.0731
Max Act: 2.7879. Min Act: -0.1700
Data Index: 4884298 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0731. Min Range: -3.0731
Max Act: 2.7879. Min Act: -0.1700
Data Index: 5948256 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0731. Min Range: -3.0731
Max Act: 2.7879. Min Act: -0.1700
Data Index: 2415612 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0731. Min Range: -3.0731
Max Act: 2.7879. Min Act: -0.1700
Data Index: 5199780 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0731. Min Range: -3.0731
Max Act: 2.8039. Min Act: -0.1700
Data Index: 2575583 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0731. Min Range: -3.0731
Max Act: 2.7560. Min Act: -0.1700
Data Index: 2649521 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0731. Min Range: -3.0731
Max Act: 2.7560. Min Act: -0.1700
Data Index: 6197678 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0731. Min Range: -3.0731
Max Act: 2.7401. Min Act: -0.1700
Data Index: 1379111 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0731. Min Range: -3.0731
Max Act: 2.7879. Min Act: -0.1700
Data Index: 5147640 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0731. Min Range: -3.0731
Max Act: 2.7720. Min Act: -0.1700
Data Index: 487496 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0731. Min Range: -3.0731
Max Act: 2.7560. Min Act: -0.1700
Data Index: 6126493 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0731. Min Range: -3.0731
Max Act: 2.7560. Min Act: -0.1700
Data Index: 3884376 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19