Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2577 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4881. Min Range: -5.4881
Max Act: 5.4881. Min Act: -0.1700
Data Index: 595172 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4881. Min Range: -5.4881
Max Act: 5.3944. Min Act: -0.1700
Data Index: 4590584 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4881. Min Range: -5.4881
Max Act: 5.1756. Min Act: -0.1700
Data Index: 1140726 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4881. Min Range: -5.4881
Max Act: 5.1444. Min Act: -0.1700
Data Index: 6292355 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4881. Min Range: -5.4881
Max Act: 5.1756. Min Act: -0.1700
Data Index: 5809172 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4881. Min Range: -5.4881
Max Act: 5.1444. Min Act: -0.1700
Data Index: 8457724 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4881. Min Range: -5.4881
Max Act: 5.1131. Min Act: -0.1700
Data Index: 8009342 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4881. Min Range: -5.4881
Max Act: 5.1131. Min Act: -0.1700
Data Index: 129859 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4881. Min Range: -5.4881
Max Act: 5.1131. Min Act: -0.1700
Data Index: 8068848 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4881. Min Range: -5.4881
Max Act: 5.0819. Min Act: -0.1700
Data Index: 7745332 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4881. Min Range: -5.4881
Max Act: 5.1131. Min Act: -0.1700
Data Index: 3368267 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4881. Min Range: -5.4881
Max Act: 5.0819. Min Act: -0.1700
Data Index: 7646387 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4881. Min Range: -5.4881
Max Act: 5.0506. Min Act: -0.1700
Data Index: 1437760 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4881. Min Range: -5.4881
Max Act: 5.0194. Min Act: -0.1700
Data Index: 3237823 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4881. Min Range: -5.4881
Max Act: 5.0194. Min Act: -0.1700
Data Index: 4827631 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4881. Min Range: -5.4881
Max Act: 5.0194. Min Act: -0.1700
Data Index: 6293944 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4881. Min Range: -5.4881
Max Act: 5.0194. Min Act: -0.1700
Data Index: 5976465 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4881. Min Range: -5.4881
Max Act: 4.9881. Min Act: -0.1700
Data Index: 2609008 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4881. Min Range: -5.4881
Max Act: 4.9881. Min Act: -0.1700
Data Index: 754980 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4881. Min Range: -5.4881
Max Act: 4.9881. Min Act: -0.1700
Data Index: 6834446 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19