Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3540 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9976. Min Range: -1.9976
Max Act: 1.9976. Min Act: -0.1700
Data Index: 1559956 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9976. Min Range: -1.9976
Max Act: 1.9297. Min Act: -0.1700
Data Index: 2741291 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9976. Min Range: -1.9976
Max Act: 1.9467. Min Act: -0.1696
Data Index: 4827619 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9976. Min Range: -1.9976
Max Act: 1.9297. Min Act: -0.1696
Data Index: 6298855 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9976. Min Range: -1.9976
Max Act: 1.9297. Min Act: -0.1700
Data Index: 2976740 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9976. Min Range: -1.9976
Max Act: 1.9212. Min Act: -0.1700
Data Index: 7363985 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9976. Min Range: -1.9976
Max Act: 1.9127. Min Act: -0.1700
Data Index: 5078129 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9976. Min Range: -1.9976
Max Act: 1.9127. Min Act: -0.1700
Data Index: 4926572 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9976. Min Range: -1.9976
Max Act: 1.8957. Min Act: -0.1700
Data Index: 7507616 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9976. Min Range: -1.9976
Max Act: 1.8957. Min Act: -0.1700
Data Index: 2538141 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9976. Min Range: -1.9976
Max Act: 1.8957. Min Act: -0.1700
Data Index: 964826 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9976. Min Range: -1.9976
Max Act: 1.8957. Min Act: -0.1700
Data Index: 629810 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9976. Min Range: -1.9976
Max Act: 1.8957. Min Act: -0.1700
Data Index: 2899766 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9976. Min Range: -1.9976
Max Act: 1.8957. Min Act: -0.1700
Data Index: 344040 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9976. Min Range: -1.9976
Max Act: 1.8786. Min Act: -0.1700
Data Index: 486919 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9976. Min Range: -1.9976
Max Act: 1.8871. Min Act: -0.1700
Data Index: 4823332 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9976. Min Range: -1.9976
Max Act: 1.8786. Min Act: -0.1697
Data Index: 5734722 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9976. Min Range: -1.9976
Max Act: 1.8871. Min Act: -0.1700
Data Index: 4307504 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9976. Min Range: -1.9976
Max Act: 1.8786. Min Act: -0.1700
Data Index: 6996338 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9976. Min Range: -1.9976
Max Act: 1.8786. Min Act: -0.1700
Data Index: 6002287 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #19