Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1792 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2572. Min Range: -7.2572
Max Act: 7.2572. Min Act: -0.1700
Data Index: 2660362 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2572. Min Range: -7.2572
Max Act: 7.2259. Min Act: -0.1700
Data Index: 3795573 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2572. Min Range: -7.2572
Max Act: 7.1947. Min Act: -0.1700
Data Index: 4719124 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2572. Min Range: -7.2572
Max Act: 7.0697. Min Act: -0.1700
Data Index: 7301356 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2572. Min Range: -7.2572
Max Act: 6.9134. Min Act: -0.1700
Data Index: 1861060 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2572. Min Range: -7.2572
Max Act: 6.9134. Min Act: -0.1700
Data Index: 4791714 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2572. Min Range: -7.2572
Max Act: 6.8822. Min Act: -0.1700
Data Index: 2813646 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2572. Min Range: -7.2572
Max Act: 6.8197. Min Act: -0.1700
Data Index: 6899431 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2572. Min Range: -7.2572
Max Act: 6.7884. Min Act: -0.1700
Data Index: 512239 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2572. Min Range: -7.2572
Max Act: 6.7259. Min Act: -0.1700
Data Index: 6166489 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2572. Min Range: -7.2572
Max Act: 6.7259. Min Act: -0.1700
Data Index: 8124183 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2572. Min Range: -7.2572
Max Act: 6.6947. Min Act: -0.1700
Data Index: 2265968 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2572. Min Range: -7.2572
Max Act: 6.6947. Min Act: -0.1700
Data Index: 8082430 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2572. Min Range: -7.2572
Max Act: 6.6947. Min Act: -0.1700
Data Index: 6436915 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2572. Min Range: -7.2572
Max Act: 6.6947. Min Act: -0.1700
Data Index: 2956251 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2572. Min Range: -7.2572
Max Act: 6.6634. Min Act: -0.1700
Data Index: 6433112 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2572. Min Range: -7.2572
Max Act: 6.6634. Min Act: -0.1700
Data Index: 5283927 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2572. Min Range: -7.2572
Max Act: 6.6322. Min Act: -0.1700
Data Index: 3329427 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2572. Min Range: -7.2572
Max Act: 6.6322. Min Act: -0.1700
Data Index: 4662376 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2572. Min Range: -7.2572
Max Act: 6.6322. Min Act: -0.1700
Data Index: 3528379 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #19