Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 496 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.5988. Min Range: -7.5988
Max Act: 7.5988. Min Act: -0.1700
Data Index: 586989 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5988. Min Range: -7.5988
Max Act: 7.5363. Min Act: -0.1700
Data Index: 5940245 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5988. Min Range: -7.5988
Max Act: 7.4426. Min Act: -0.1700
Data Index: 2474781 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5988. Min Range: -7.5988
Max Act: 7.4426. Min Act: -0.1700
Data Index: 5262601 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5988. Min Range: -7.5988
Max Act: 7.3176. Min Act: -0.1700
Data Index: 2489556 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5988. Min Range: -7.5988
Max Act: 7.2238. Min Act: -0.1700
Data Index: 5452292 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5988. Min Range: -7.5988
Max Act: 7.1301. Min Act: -0.1700
Data Index: 8726713 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5988. Min Range: -7.5988
Max Act: 7.0988. Min Act: -0.1700
Data Index: 8409105 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5988. Min Range: -7.5988
Max Act: 7.0988. Min Act: -0.1700
Data Index: 968121 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5988. Min Range: -7.5988
Max Act: 7.0363. Min Act: -0.1700
Data Index: 4861875 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5988. Min Range: -7.5988
Max Act: 7.0676. Min Act: -0.1700
Data Index: 392765 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5988. Min Range: -7.5988
Max Act: 7.0676. Min Act: -0.1700
Data Index: 5837684 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5988. Min Range: -7.5988
Max Act: 7.0676. Min Act: -0.1700
Data Index: 4558803 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5988. Min Range: -7.5988
Max Act: 7.0051. Min Act: -0.1700
Data Index: 7508728 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5988. Min Range: -7.5988
Max Act: 7.0051. Min Act: -0.1700
Data Index: 2890633 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5988. Min Range: -7.5988
Max Act: 6.9426. Min Act: -0.1700
Data Index: 1348101 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5988. Min Range: -7.5988
Max Act: 6.9426. Min Act: -0.1700
Data Index: 2248731 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5988. Min Range: -7.5988
Max Act: 6.9738. Min Act: -0.1700
Data Index: 7255443 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5988. Min Range: -7.5988
Max Act: 6.9738. Min Act: -0.1700
Data Index: 1019556 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5988. Min Range: -7.5988
Max Act: 6.9426. Min Act: -0.1700
Data Index: 2362514 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19