Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1924 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6428. Min Range: -7.6428
Max Act: 7.6428. Min Act: -0.1700
Data Index: 2792233 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6428. Min Range: -7.6428
Max Act: 7.5178. Min Act: -0.1700
Data Index: 3123451 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6428. Min Range: -7.6428
Max Act: 7.3928. Min Act: -0.1700
Data Index: 1070669 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6428. Min Range: -7.6428
Max Act: 7.3303. Min Act: -0.1700
Data Index: 6487791 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6428. Min Range: -7.6428
Max Act: 7.2365. Min Act: -0.1700
Data Index: 1690653 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6428. Min Range: -7.6428
Max Act: 7.1428. Min Act: -0.1700
Data Index: 6107794 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6428. Min Range: -7.6428
Max Act: 7.1428. Min Act: -0.1700
Data Index: 3176978 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6428. Min Range: -7.6428
Max Act: 7.1115. Min Act: -0.1700
Data Index: 2242427 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6428. Min Range: -7.6428
Max Act: 7.1115. Min Act: -0.1700
Data Index: 8499181 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6428. Min Range: -7.6428
Max Act: 7.0490. Min Act: -0.1700
Data Index: 5945464 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6428. Min Range: -7.6428
Max Act: 7.0178. Min Act: -0.1700
Data Index: 3489890 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6428. Min Range: -7.6428
Max Act: 6.9865. Min Act: -0.1700
Data Index: 5766225 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6428. Min Range: -7.6428
Max Act: 6.9865. Min Act: -0.1700
Data Index: 5226547 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6428. Min Range: -7.6428
Max Act: 6.9865. Min Act: -0.1700
Data Index: 6808437 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6428. Min Range: -7.6428
Max Act: 6.9553. Min Act: -0.1700
Data Index: 1627835 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6428. Min Range: -7.6428
Max Act: 6.9240. Min Act: -0.1700
Data Index: 3533214 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6428. Min Range: -7.6428
Max Act: 6.9240. Min Act: -0.1700
Data Index: 2992963 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6428. Min Range: -7.6428
Max Act: 6.9240. Min Act: -0.1700
Data Index: 6570514 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6428. Min Range: -7.6428
Max Act: 6.7990. Min Act: -0.1700
Data Index: 3151813 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6428. Min Range: -7.6428
Max Act: 6.8303. Min Act: -0.1700
Data Index: 7813342 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19