Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1985 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3287. Min Range: -9.3287
Max Act: 9.3287. Min Act: -0.1700
Data Index: 971448 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3287. Min Range: -9.3287
Max Act: 8.8287. Min Act: -0.1700
Data Index: 6862534 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3287. Min Range: -9.3287
Max Act: 8.5787. Min Act: -0.1700
Data Index: 6665455 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3287. Min Range: -9.3287
Max Act: 8.5162. Min Act: -0.1700
Data Index: 2986935 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3287. Min Range: -9.3287
Max Act: 8.3287. Min Act: -0.1700
Data Index: 2781848 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3287. Min Range: -9.3287
Max Act: 8.3287. Min Act: -0.1700
Data Index: 3083721 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3287. Min Range: -9.3287
Max Act: 8.2037. Min Act: -0.1700
Data Index: 3679767 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3287. Min Range: -9.3287
Max Act: 8.2662. Min Act: -0.1700
Data Index: 6691195 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3287. Min Range: -9.3287
Max Act: 8.2662. Min Act: -0.1700
Data Index: 3083720 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3287. Min Range: -9.3287
Max Act: 8.2037. Min Act: -0.1700
Data Index: 8020130 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3287. Min Range: -9.3287
Max Act: 8.1412. Min Act: -0.1700
Data Index: 3018137 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3287. Min Range: -9.3287
Max Act: 8.2037. Min Act: -0.1700
Data Index: 5438493 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3287. Min Range: -9.3287
Max Act: 8.1412. Min Act: -0.1700
Data Index: 5438506 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3287. Min Range: -9.3287
Max Act: 8.1412. Min Act: -0.1700
Data Index: 279013 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3287. Min Range: -9.3287
Max Act: 8.1412. Min Act: -0.1700
Data Index: 1305859 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3287. Min Range: -9.3287
Max Act: 8.0787. Min Act: -0.1700
Data Index: 163058 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3287. Min Range: -9.3287
Max Act: 8.1412. Min Act: -0.1700
Data Index: 4897968 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3287. Min Range: -9.3287
Max Act: 8.1412. Min Act: -0.1700
Data Index: 5717499 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3287. Min Range: -9.3287
Max Act: 8.0162. Min Act: -0.1700
Data Index: 7280975 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3287. Min Range: -9.3287
Max Act: 8.0787. Min Act: -0.1700
Data Index: 2388428 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19