Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3364 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6634. Min Range: -6.6634
Max Act: 6.6634. Min Act: -0.1700
Data Index: 3555530 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6634. Min Range: -6.6634
Max Act: 6.3821. Min Act: -0.1700
Data Index: 3770046 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6634. Min Range: -6.6634
Max Act: 6.2884. Min Act: -0.1700
Data Index: 6786807 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6634. Min Range: -6.6634
Max Act: 6.2571. Min Act: -0.1700
Data Index: 4263444 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6634. Min Range: -6.6634
Max Act: 6.2259. Min Act: -0.1700
Data Index: 5009075 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6634. Min Range: -6.6634
Max Act: 6.2259. Min Act: -0.1700
Data Index: 2342506 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6634. Min Range: -6.6634
Max Act: 6.2259. Min Act: -0.1700
Data Index: 7598392 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6634. Min Range: -6.6634
Max Act: 6.2259. Min Act: -0.1700
Data Index: 1567243 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6634. Min Range: -6.6634
Max Act: 6.1946. Min Act: -0.1700
Data Index: 1358927 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6634. Min Range: -6.6634
Max Act: 6.1946. Min Act: -0.1700
Data Index: 7622271 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6634. Min Range: -6.6634
Max Act: 6.1634. Min Act: -0.1700
Data Index: 2016293 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6634. Min Range: -6.6634
Max Act: 6.1634. Min Act: -0.1700
Data Index: 771735 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6634. Min Range: -6.6634
Max Act: 6.1634. Min Act: -0.1700
Data Index: 3555531 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6634. Min Range: -6.6634
Max Act: 6.1321. Min Act: -0.1700
Data Index: 3854845 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6634. Min Range: -6.6634
Max Act: 6.1634. Min Act: -0.1700
Data Index: 807850 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6634. Min Range: -6.6634
Max Act: 6.1321. Min Act: -0.1700
Data Index: 5223002 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6634. Min Range: -6.6634
Max Act: 6.1009. Min Act: -0.1700
Data Index: 8437551 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6634. Min Range: -6.6634
Max Act: 6.1009. Min Act: -0.1700
Data Index: 173800 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6634. Min Range: -6.6634
Max Act: 6.1009. Min Act: -0.1700
Data Index: 3700481 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6634. Min Range: -6.6634
Max Act: 6.1009. Min Act: -0.1700
Data Index: 6486481 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #19