Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3045 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3562. Min Range: -5.3562
Max Act: 5.3562. Min Act: -0.1700
Data Index: 3867076 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3562. Min Range: -5.3562
Max Act: 5.2937. Min Act: -0.1700
Data Index: 865601 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3562. Min Range: -5.3562
Max Act: 5.2937. Min Act: -0.1700
Data Index: 8640863 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3562. Min Range: -5.3562
Max Act: 5.2312. Min Act: -0.1700
Data Index: 4568215 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3562. Min Range: -5.3562
Max Act: 5.2000. Min Act: -0.1700
Data Index: 3308184 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3562. Min Range: -5.3562
Max Act: 5.1687. Min Act: -0.1700
Data Index: 7369459 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3562. Min Range: -5.3562
Max Act: 5.1375. Min Act: -0.1700
Data Index: 5517685 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3562. Min Range: -5.3562
Max Act: 5.1687. Min Act: -0.1700
Data Index: 5674265 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3562. Min Range: -5.3562
Max Act: 5.1375. Min Act: -0.1700
Data Index: 5811186 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3562. Min Range: -5.3562
Max Act: 5.2000. Min Act: -0.1700
Data Index: 5350226 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3562. Min Range: -5.3562
Max Act: 5.1375. Min Act: -0.1700
Data Index: 3444155 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3562. Min Range: -5.3562
Max Act: 5.1062. Min Act: -0.1700
Data Index: 7040535 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3562. Min Range: -5.3562
Max Act: 5.1062. Min Act: -0.1700
Data Index: 801147 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3562. Min Range: -5.3562
Max Act: 5.1062. Min Act: -0.1700
Data Index: 2429791 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3562. Min Range: -5.3562
Max Act: 5.1062. Min Act: -0.1700
Data Index: 2601335 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3562. Min Range: -5.3562
Max Act: 5.0437. Min Act: -0.1700
Data Index: 3031069 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3562. Min Range: -5.3562
Max Act: 5.0437. Min Act: -0.1700
Data Index: 4357237 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3562. Min Range: -5.3562
Max Act: 5.0750. Min Act: -0.1700
Data Index: 8035712 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3562. Min Range: -5.3562
Max Act: 5.0750. Min Act: -0.1700
Data Index: 6977713 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3562. Min Range: -5.3562
Max Act: 5.0437. Min Act: -0.1700
Data Index: 4559118 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19