Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4300 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8110. Min Range: -8.8110
Max Act: 8.8110. Min Act: -0.1700
Data Index: 6759803 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8110. Min Range: -8.8110
Max Act: 8.8110. Min Act: -0.1700
Data Index: 8028491 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8110. Min Range: -8.8110
Max Act: 8.6235. Min Act: -0.1700
Data Index: 12849 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8110. Min Range: -8.8110
Max Act: 8.5610. Min Act: -0.1700
Data Index: 5084998 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8110. Min Range: -8.8110
Max Act: 8.3735. Min Act: -0.1700
Data Index: 3547272 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8110. Min Range: -8.8110
Max Act: 8.3110. Min Act: -0.1700
Data Index: 5780658 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8110. Min Range: -8.8110
Max Act: 8.2485. Min Act: -0.1700
Data Index: 4970901 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8110. Min Range: -8.8110
Max Act: 8.2485. Min Act: -0.1700
Data Index: 920231 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8110. Min Range: -8.8110
Max Act: 8.1235. Min Act: -0.1700
Data Index: 8542294 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8110. Min Range: -8.8110
Max Act: 7.9985. Min Act: -0.1700
Data Index: 1821613 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8110. Min Range: -8.8110
Max Act: 7.9985. Min Act: -0.1700
Data Index: 5780670 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8110. Min Range: -8.8110
Max Act: 7.9985. Min Act: -0.1700
Data Index: 6757705 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8110. Min Range: -8.8110
Max Act: 7.9985. Min Act: -0.1700
Data Index: 6757716 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8110. Min Range: -8.8110
Max Act: 7.9672. Min Act: -0.1700
Data Index: 511208 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8110. Min Range: -8.8110
Max Act: 7.9360. Min Act: -0.1700
Data Index: 1919185 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8110. Min Range: -8.8110
Max Act: 7.8735. Min Act: -0.1700
Data Index: 1697549 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8110. Min Range: -8.8110
Max Act: 7.8422. Min Act: -0.1700
Data Index: 920230 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8110. Min Range: -8.8110
Max Act: 7.8422. Min Act: -0.1700
Data Index: 7165405 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8110. Min Range: -8.8110
Max Act: 7.8422. Min Act: -0.1700
Data Index: 4970915 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8110. Min Range: -8.8110
Max Act: 7.8422. Min Act: -0.1700
Data Index: 1935526 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19