Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2503 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1006. Min Range: -7.1006
Max Act: 7.1006. Min Act: -0.1700
Data Index: 4730199 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1006. Min Range: -7.1006
Max Act: 7.1006. Min Act: -0.1700
Data Index: 6183532 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1006. Min Range: -7.1006
Max Act: 6.7881. Min Act: -0.1700
Data Index: 117417 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1006. Min Range: -7.1006
Max Act: 6.7569. Min Act: -0.1700
Data Index: 5979615 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1006. Min Range: -7.1006
Max Act: 6.6319. Min Act: -0.1700
Data Index: 6398521 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1006. Min Range: -7.1006
Max Act: 6.6631. Min Act: -0.1700
Data Index: 8377515 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1006. Min Range: -7.1006
Max Act: 6.5694. Min Act: -0.1700
Data Index: 3489785 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1006. Min Range: -7.1006
Max Act: 6.5381. Min Act: -0.1700
Data Index: 1970818 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1006. Min Range: -7.1006
Max Act: 6.5069. Min Act: -0.1700
Data Index: 5298407 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1006. Min Range: -7.1006
Max Act: 6.4444. Min Act: -0.1700
Data Index: 6574004 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1006. Min Range: -7.1006
Max Act: 6.5069. Min Act: -0.1700
Data Index: 2728189 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1006. Min Range: -7.1006
Max Act: 6.4444. Min Act: -0.1700
Data Index: 8369282 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1006. Min Range: -7.1006
Max Act: 6.4131. Min Act: -0.1700
Data Index: 3426042 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1006. Min Range: -7.1006
Max Act: 6.4131. Min Act: -0.1700
Data Index: 7217037 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1006. Min Range: -7.1006
Max Act: 6.4131. Min Act: -0.1700
Data Index: 2676866 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1006. Min Range: -7.1006
Max Act: 6.3819. Min Act: -0.1700
Data Index: 1656785 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1006. Min Range: -7.1006
Max Act: 6.3819. Min Act: -0.1700
Data Index: 2592969 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1006. Min Range: -7.1006
Max Act: 6.3194. Min Act: -0.1700
Data Index: 1421234 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1006. Min Range: -7.1006
Max Act: 6.3194. Min Act: -0.1700
Data Index: 1983779 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1006. Min Range: -7.1006
Max Act: 6.2569. Min Act: -0.1700
Data Index: 5950353 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #19