Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2914 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2638. Min Range: -6.2638
Max Act: 6.2638. Min Act: -0.1700
Data Index: 7671241 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2638. Min Range: -6.2638
Max Act: 6.1700. Min Act: -0.1700
Data Index: 4956864 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2638. Min Range: -6.2638
Max Act: 6.1388. Min Act: -0.1700
Data Index: 2217693 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2638. Min Range: -6.2638
Max Act: 6.1075. Min Act: -0.1700
Data Index: 7056970 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2638. Min Range: -6.2638
Max Act: 6.0763. Min Act: -0.1700
Data Index: 1603924 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2638. Min Range: -6.2638
Max Act: 6.0763. Min Act: -0.1700
Data Index: 175954 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2638. Min Range: -6.2638
Max Act: 6.0138. Min Act: -0.1700
Data Index: 5948800 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2638. Min Range: -6.2638
Max Act: 5.9825. Min Act: -0.1700
Data Index: 4504557 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2638. Min Range: -6.2638
Max Act: 5.9825. Min Act: -0.1700
Data Index: 7865438 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2638. Min Range: -6.2638
Max Act: 5.9825. Min Act: -0.1700
Data Index: 2153349 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2638. Min Range: -6.2638
Max Act: 5.9200. Min Act: -0.1700
Data Index: 4142798 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2638. Min Range: -6.2638
Max Act: 5.8888. Min Act: -0.1700
Data Index: 8504135 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2638. Min Range: -6.2638
Max Act: 5.8888. Min Act: -0.1700
Data Index: 7623413 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2638. Min Range: -6.2638
Max Act: 5.8888. Min Act: -0.1700
Data Index: 7600052 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2638. Min Range: -6.2638
Max Act: 5.8575. Min Act: -0.1700
Data Index: 5130542 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2638. Min Range: -6.2638
Max Act: 5.8575. Min Act: -0.1700
Data Index: 7201467 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2638. Min Range: -6.2638
Max Act: 5.8263. Min Act: -0.1700
Data Index: 4415471 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2638. Min Range: -6.2638
Max Act: 5.7950. Min Act: -0.1700
Data Index: 4280209 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2638. Min Range: -6.2638
Max Act: 5.7638. Min Act: -0.1700
Data Index: 7255484 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2638. Min Range: -6.2638
Max Act: 5.7638. Min Act: -0.1700
Data Index: 5457334 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19