Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1941 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3857. Min Range: -6.3857
Max Act: 6.3857. Min Act: -0.1700
Data Index: 8831886 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3857. Min Range: -6.3857
Max Act: 6.0107. Min Act: -0.1700
Data Index: 1254637 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3857. Min Range: -6.3857
Max Act: 5.9795. Min Act: -0.1700
Data Index: 2295526 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3857. Min Range: -6.3857
Max Act: 5.8232. Min Act: -0.1700
Data Index: 2754980 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3857. Min Range: -6.3857
Max Act: 5.7607. Min Act: -0.1700
Data Index: 2516341 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3857. Min Range: -6.3857
Max Act: 5.7607. Min Act: -0.1700
Data Index: 673020 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3857. Min Range: -6.3857
Max Act: 5.7295. Min Act: -0.1700
Data Index: 191898 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3857. Min Range: -6.3857
Max Act: 5.6982. Min Act: -0.1700
Data Index: 3518293 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3857. Min Range: -6.3857
Max Act: 5.6982. Min Act: -0.1700
Data Index: 3569154 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3857. Min Range: -6.3857
Max Act: 5.7295. Min Act: -0.1700
Data Index: 8381768 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3857. Min Range: -6.3857
Max Act: 5.6670. Min Act: -0.1700
Data Index: 7923928 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3857. Min Range: -6.3857
Max Act: 5.6045. Min Act: -0.1700
Data Index: 6051702 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3857. Min Range: -6.3857
Max Act: 5.6357. Min Act: -0.1700
Data Index: 1012788 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3857. Min Range: -6.3857
Max Act: 5.6045. Min Act: -0.1700
Data Index: 3573320 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3857. Min Range: -6.3857
Max Act: 5.5732. Min Act: -0.1700
Data Index: 5067552 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3857. Min Range: -6.3857
Max Act: 5.6045. Min Act: -0.1700
Data Index: 4547686 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3857. Min Range: -6.3857
Max Act: 5.6045. Min Act: -0.1700
Data Index: 4345740 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3857. Min Range: -6.3857
Max Act: 5.6357. Min Act: -0.1700
Data Index: 7015817 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3857. Min Range: -6.3857
Max Act: 5.5732. Min Act: -0.1700
Data Index: 3598364 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3857. Min Range: -6.3857
Max Act: 5.5732. Min Act: -0.1700
Data Index: 6922549 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19