Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5716 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.2803. Min Range: -15.2803
Max Act: 15.2803. Min Act: -0.1700
Data Index: 1177906 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.2803. Min Range: -15.2803
Max Act: 15.0303. Min Act: -0.1700
Data Index: 2200460 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.2803. Min Range: -15.2803
Max Act: 15.0303. Min Act: -0.1700
Data Index: 6156305 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.2803. Min Range: -15.2803
Max Act: 14.9053. Min Act: -0.1700
Data Index: 8715109 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.2803. Min Range: -15.2803
Max Act: 14.5303. Min Act: -0.1700
Data Index: 3175788 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.2803. Min Range: -15.2803
Max Act: 14.5928. Min Act: -0.1700
Data Index: 6900859 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.2803. Min Range: -15.2803
Max Act: 14.5303. Min Act: -0.1700
Data Index: 7685008 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.2803. Min Range: -15.2803
Max Act: 14.4053. Min Act: -0.1700
Data Index: 1555529 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.2803. Min Range: -15.2803
Max Act: 14.4053. Min Act: -0.1700
Data Index: 6883153 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.2803. Min Range: -15.2803
Max Act: 14.3428. Min Act: -0.1700
Data Index: 1456544 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.2803. Min Range: -15.2803
Max Act: 14.2803. Min Act: -0.1700
Data Index: 369189 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.2803. Min Range: -15.2803
Max Act: 14.2178. Min Act: -0.1700
Data Index: 4026173 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.2803. Min Range: -15.2803
Max Act: 14.2803. Min Act: -0.1700
Data Index: 8161545 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.2803. Min Range: -15.2803
Max Act: 14.2178. Min Act: -0.1700
Data Index: 6477630 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.2803. Min Range: -15.2803
Max Act: 14.2178. Min Act: -0.1700
Data Index: 3750938 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.2803. Min Range: -15.2803
Max Act: 14.1553. Min Act: -0.1700
Data Index: 2221154 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.2803. Min Range: -15.2803
Max Act: 14.2178. Min Act: -0.1700
Data Index: 8009276 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.2803. Min Range: -15.2803
Max Act: 14.2178. Min Act: -0.1700
Data Index: 3539560 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.2803. Min Range: -15.2803
Max Act: 14.2803. Min Act: -0.1700
Data Index: 2169920 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.2803. Min Range: -15.2803
Max Act: 14.2178. Min Act: -0.1700
Data Index: 5765077 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19