Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5214 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.8306. Min Act: -0.1700
Data Index: 2099272 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.7369. Min Act: -0.1700
Data Index: 200915 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.6744. Min Act: -0.1700
Data Index: 1064865 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.5494. Min Act: -0.1700
Data Index: 3593276 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.3619. Min Act: -0.1700
Data Index: 2099268 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.3619. Min Act: -0.1700
Data Index: 5944864 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.3619. Min Act: -0.1700
Data Index: 3421463 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.3619. Min Act: -0.1700
Data Index: 4345727 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.3931. Min Act: -0.1700
Data Index: 1122175 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.3619. Min Act: -0.1700
Data Index: 96945 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.3619. Min Act: -0.1700
Data Index: 6212909 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.3306. Min Act: -0.1700
Data Index: 4897792 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.3306. Min Act: -0.1700
Data Index: 1939696 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.2994. Min Act: -0.1700
Data Index: 1734938 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.2994. Min Act: -0.1700
Data Index: 8609039 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.2681. Min Act: -0.1700
Data Index: 2516124 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.2994. Min Act: -0.1700
Data Index: 5620489 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.2368. Min Act: -0.1700
Data Index: 998495 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.2681. Min Act: -0.1700
Data Index: 6099441 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.2368. Min Act: -0.1700
Data Index: 1569526 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19