Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 281 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.4440. Min Act: -0.1700
Data Index: 355042 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.4440. Min Act: -0.1700
Data Index: 5353632 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.3815. Min Act: -0.1700
Data Index: 5427943 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.3815. Min Act: -0.1700
Data Index: 360268 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.4128. Min Act: -0.1700
Data Index: 4684687 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.3815. Min Act: -0.1700
Data Index: 6069968 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.3190. Min Act: -0.1700
Data Index: 1940045 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.2565. Min Act: -0.1700
Data Index: 6017199 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.3190. Min Act: -0.1700
Data Index: 7936901 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.3190. Min Act: -0.1700
Data Index: 3069215 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.2565. Min Act: -0.1700
Data Index: 5957023 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.2253. Min Act: -0.1700
Data Index: 4406067 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.2253. Min Act: -0.1700
Data Index: 3146144 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.1940. Min Act: -0.1700
Data Index: 3519978 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.1940. Min Act: -0.1700
Data Index: 238670 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.1940. Min Act: -0.1700
Data Index: 3479050 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.2253. Min Act: -0.1700
Data Index: 7818821 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.1940. Min Act: -0.1700
Data Index: 8754976 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.2253. Min Act: -0.1700
Data Index: 5732717 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.1628. Min Act: -0.1700
Data Index: 603445 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19