Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3084 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3033. Min Range: -6.3033
Max Act: 6.3033. Min Act: -0.1700
Data Index: 350396 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3033. Min Range: -6.3033
Max Act: 6.2720. Min Act: -0.1700
Data Index: 6857076 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3033. Min Range: -6.3033
Max Act: 6.0845. Min Act: -0.1700
Data Index: 5695132 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3033. Min Range: -6.3033
Max Act: 6.0220. Min Act: -0.1700
Data Index: 3717169 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3033. Min Range: -6.3033
Max Act: 5.9595. Min Act: -0.1700
Data Index: 2538217 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3033. Min Range: -6.3033
Max Act: 5.8970. Min Act: -0.1700
Data Index: 6145518 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3033. Min Range: -6.3033
Max Act: 5.8970. Min Act: -0.1700
Data Index: 8459230 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3033. Min Range: -6.3033
Max Act: 5.8970. Min Act: -0.1700
Data Index: 4980051 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3033. Min Range: -6.3033
Max Act: 5.8658. Min Act: -0.1700
Data Index: 4245088 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3033. Min Range: -6.3033
Max Act: 5.8345. Min Act: -0.1700
Data Index: 1217391 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3033. Min Range: -6.3033
Max Act: 5.8033. Min Act: -0.1700
Data Index: 6679659 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3033. Min Range: -6.3033
Max Act: 5.8033. Min Act: -0.1700
Data Index: 4759880 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3033. Min Range: -6.3033
Max Act: 5.8033. Min Act: -0.1700
Data Index: 5995281 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3033. Min Range: -6.3033
Max Act: 5.7720. Min Act: -0.1700
Data Index: 8316532 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3033. Min Range: -6.3033
Max Act: 5.7720. Min Act: -0.1700
Data Index: 7350026 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3033. Min Range: -6.3033
Max Act: 5.7408. Min Act: -0.1700
Data Index: 4483400 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3033. Min Range: -6.3033
Max Act: 5.7408. Min Act: -0.1700
Data Index: 5878491 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3033. Min Range: -6.3033
Max Act: 5.7408. Min Act: -0.1700
Data Index: 8107744 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3033. Min Range: -6.3033
Max Act: 5.6783. Min Act: -0.1700
Data Index: 8165097 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3033. Min Range: -6.3033
Max Act: 5.7095. Min Act: -0.1700
Data Index: 3703891 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19