Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 21 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5713. Min Range: -4.5713
Max Act: 4.5713. Min Act: -0.1700
Data Index: 980521 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5713. Min Range: -4.5713
Max Act: 4.5713. Min Act: -0.1700
Data Index: 5218336 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5713. Min Range: -4.5713
Max Act: 4.5400. Min Act: -0.1700
Data Index: 7279064 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5713. Min Range: -4.5713
Max Act: 4.5088. Min Act: -0.1700
Data Index: 6476603 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5713. Min Range: -4.5713
Max Act: 4.5088. Min Act: -0.1700
Data Index: 4282655 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5713. Min Range: -4.5713
Max Act: 4.5088. Min Act: -0.1700
Data Index: 384976 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5713. Min Range: -4.5713
Max Act: 4.5088. Min Act: -0.1700
Data Index: 121667 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5713. Min Range: -4.5713
Max Act: 4.4775. Min Act: -0.1700
Data Index: 7686063 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5713. Min Range: -4.5713
Max Act: 4.4775. Min Act: -0.1700
Data Index: 4243556 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5713. Min Range: -4.5713
Max Act: 4.4775. Min Act: -0.1700
Data Index: 3022321 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5713. Min Range: -4.5713
Max Act: 4.4463. Min Act: -0.1700
Data Index: 7576428 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5713. Min Range: -4.5713
Max Act: 4.4463. Min Act: -0.1700
Data Index: 8825281 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5713. Min Range: -4.5713
Max Act: 4.4463. Min Act: -0.1700
Data Index: 5633929 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5713. Min Range: -4.5713
Max Act: 4.4150. Min Act: -0.1700
Data Index: 2977493 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5713. Min Range: -4.5713
Max Act: 4.4150. Min Act: -0.1700
Data Index: 1669446 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5713. Min Range: -4.5713
Max Act: 4.3525. Min Act: -0.1700
Data Index: 330285 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5713. Min Range: -4.5713
Max Act: 4.3838. Min Act: -0.1700
Data Index: 3060956 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5713. Min Range: -4.5713
Max Act: 4.3838. Min Act: -0.1700
Data Index: 6225402 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5713. Min Range: -4.5713
Max Act: 4.3838. Min Act: -0.1700
Data Index: 209924 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5713. Min Range: -4.5713
Max Act: 4.3838. Min Act: -0.1700
Data Index: 6964479 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19