Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2514 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7365. Min Range: -1.7365
Max Act: 1.7365. Min Act: -0.1700
Data Index: 3094437 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7365. Min Range: -1.7365
Max Act: 1.6932. Min Act: -0.1700
Data Index: 3556843 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7365. Min Range: -1.7365
Max Act: 1.6932. Min Act: -0.1700
Data Index: 8521665 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7365. Min Range: -1.7365
Max Act: 1.6845. Min Act: -0.1700
Data Index: 7201737 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7365. Min Range: -1.7365
Max Act: 1.6672. Min Act: -0.1700
Data Index: 8257186 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7365. Min Range: -1.7365
Max Act: 1.6411. Min Act: -0.1700
Data Index: 6645055 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7365. Min Range: -1.7365
Max Act: 1.6498. Min Act: -0.1700
Data Index: 277921 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7365. Min Range: -1.7365
Max Act: 1.6411. Min Act: -0.1700
Data Index: 8497716 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7365. Min Range: -1.7365
Max Act: 1.6324. Min Act: -0.1700
Data Index: 8382174 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7365. Min Range: -1.7365
Max Act: 1.6411. Min Act: -0.1700
Data Index: 8180234 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7365. Min Range: -1.7365
Max Act: 1.6236. Min Act: -0.1700
Data Index: 5498898 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7365. Min Range: -1.7365
Max Act: 1.6236. Min Act: -0.1699
Data Index: 2121030 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7365. Min Range: -1.7365
Max Act: 1.6236. Min Act: -0.1700
Data Index: 1918954 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7365. Min Range: -1.7365
Max Act: 1.6236. Min Act: -0.1700
Data Index: 3895270 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7365. Min Range: -1.7365
Max Act: 1.6236. Min Act: -0.1695
Data Index: 7748800 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7365. Min Range: -1.7365
Max Act: 1.6149. Min Act: -0.1700
Data Index: 6388474 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7365. Min Range: -1.7365
Max Act: 1.6149. Min Act: -0.1700
Data Index: 8520009 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7365. Min Range: -1.7365
Max Act: 1.6149. Min Act: -0.1700
Data Index: 8229482 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7365. Min Range: -1.7365
Max Act: 1.6236. Min Act: -0.1700
Data Index: 926841 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7365. Min Range: -1.7365
Max Act: 1.6236. Min Act: -0.1700
Data Index: 6944233 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19