Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1667 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5593. Min Range: -6.5593
Max Act: 6.5593. Min Act: -0.1700
Data Index: 2102817 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5593. Min Range: -6.5593
Max Act: 6.4655. Min Act: -0.1700
Data Index: 564190 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5593. Min Range: -6.5593
Max Act: 6.3405. Min Act: -0.1700
Data Index: 5892769 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5593. Min Range: -6.5593
Max Act: 6.3718. Min Act: -0.1700
Data Index: 2709009 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5593. Min Range: -6.5593
Max Act: 6.3405. Min Act: -0.1700
Data Index: 2336476 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5593. Min Range: -6.5593
Max Act: 6.3093. Min Act: -0.1700
Data Index: 4879270 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5593. Min Range: -6.5593
Max Act: 6.3093. Min Act: -0.1700
Data Index: 309983 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5593. Min Range: -6.5593
Max Act: 6.3405. Min Act: -0.1700
Data Index: 8536178 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5593. Min Range: -6.5593
Max Act: 6.3718. Min Act: -0.1700
Data Index: 2533826 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5593. Min Range: -6.5593
Max Act: 6.2780. Min Act: -0.1700
Data Index: 1743092 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5593. Min Range: -6.5593
Max Act: 6.2468. Min Act: -0.1700
Data Index: 7181924 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5593. Min Range: -6.5593
Max Act: 6.1843. Min Act: -0.1700
Data Index: 8344006 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5593. Min Range: -6.5593
Max Act: 6.1843. Min Act: -0.1700
Data Index: 3514589 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5593. Min Range: -6.5593
Max Act: 6.2155. Min Act: -0.1700
Data Index: 8482270 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5593. Min Range: -6.5593
Max Act: 6.1530. Min Act: -0.1700
Data Index: 564194 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5593. Min Range: -6.5593
Max Act: 6.2468. Min Act: -0.1700
Data Index: 564192 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5593. Min Range: -6.5593
Max Act: 6.1530. Min Act: -0.1700
Data Index: 2699827 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5593. Min Range: -6.5593
Max Act: 6.2468. Min Act: -0.1700
Data Index: 564193 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5593. Min Range: -6.5593
Max Act: 6.1218. Min Act: -0.1700
Data Index: 564189 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5593. Min Range: -6.5593
Max Act: 6.1530. Min Act: -0.1700
Data Index: 5090885 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19