Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1370 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5069. Min Range: -6.5069
Max Act: 6.5069. Min Act: -0.1700
Data Index: 5455392 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5069. Min Range: -6.5069
Max Act: 6.4756. Min Act: -0.1700
Data Index: 3073258 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5069. Min Range: -6.5069
Max Act: 6.4131. Min Act: -0.1700
Data Index: 1309602 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5069. Min Range: -6.5069
Max Act: 6.3819. Min Act: -0.1700
Data Index: 7134108 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5069. Min Range: -6.5069
Max Act: 6.3819. Min Act: -0.1700
Data Index: 1015426 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5069. Min Range: -6.5069
Max Act: 6.3819. Min Act: -0.1700
Data Index: 5325306 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5069. Min Range: -6.5069
Max Act: 6.2569. Min Act: -0.1700
Data Index: 5569759 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5069. Min Range: -6.5069
Max Act: 6.2881. Min Act: -0.1700
Data Index: 1349701 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5069. Min Range: -6.5069
Max Act: 6.2256. Min Act: -0.1700
Data Index: 2802477 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5069. Min Range: -6.5069
Max Act: 6.2256. Min Act: -0.1700
Data Index: 2623591 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5069. Min Range: -6.5069
Max Act: 6.1944. Min Act: -0.1700
Data Index: 1197418 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5069. Min Range: -6.5069
Max Act: 6.1631. Min Act: -0.1700
Data Index: 4991576 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5069. Min Range: -6.5069
Max Act: 6.1944. Min Act: -0.1700
Data Index: 6701456 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5069. Min Range: -6.5069
Max Act: 6.1631. Min Act: -0.1700
Data Index: 3269396 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5069. Min Range: -6.5069
Max Act: 6.1631. Min Act: -0.1700
Data Index: 6183885 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5069. Min Range: -6.5069
Max Act: 6.1319. Min Act: -0.1700
Data Index: 7389869 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5069. Min Range: -6.5069
Max Act: 6.1631. Min Act: -0.1700
Data Index: 2309747 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5069. Min Range: -6.5069
Max Act: 6.1319. Min Act: -0.1700
Data Index: 5740969 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5069. Min Range: -6.5069
Max Act: 6.1319. Min Act: -0.1700
Data Index: 747506 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5069. Min Range: -6.5069
Max Act: 6.1006. Min Act: -0.1700
Data Index: 5480754 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19