Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2516 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6957. Min Range: -5.6957
Max Act: 5.6957. Min Act: -0.1700
Data Index: 1594238 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6957. Min Range: -5.6957
Max Act: 5.4144. Min Act: -0.1700
Data Index: 5487389 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6957. Min Range: -5.6957
Max Act: 5.3519. Min Act: -0.1700
Data Index: 637764 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6957. Min Range: -5.6957
Max Act: 5.3519. Min Act: -0.1700
Data Index: 483133 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6957. Min Range: -5.6957
Max Act: 5.2894. Min Act: -0.1700
Data Index: 5162526 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6957. Min Range: -5.6957
Max Act: 5.2894. Min Act: -0.1700
Data Index: 6397863 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6957. Min Range: -5.6957
Max Act: 5.2894. Min Act: -0.1700
Data Index: 3838626 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6957. Min Range: -5.6957
Max Act: 5.2582. Min Act: -0.1700
Data Index: 7030365 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6957. Min Range: -5.6957
Max Act: 5.2269. Min Act: -0.1700
Data Index: 8822191 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6957. Min Range: -5.6957
Max Act: 5.1957. Min Act: -0.1700
Data Index: 5602574 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6957. Min Range: -5.6957
Max Act: 5.1644. Min Act: -0.1700
Data Index: 5086148 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6957. Min Range: -5.6957
Max Act: 5.1644. Min Act: -0.1700
Data Index: 19766 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6957. Min Range: -5.6957
Max Act: 5.1957. Min Act: -0.1700
Data Index: 8528562 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6957. Min Range: -5.6957
Max Act: 5.1644. Min Act: -0.1700
Data Index: 2493680 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6957. Min Range: -5.6957
Max Act: 5.1332. Min Act: -0.1700
Data Index: 7560046 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6957. Min Range: -5.6957
Max Act: 5.1332. Min Act: -0.1700
Data Index: 8025754 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6957. Min Range: -5.6957
Max Act: 5.1019. Min Act: -0.1700
Data Index: 4566115 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6957. Min Range: -5.6957
Max Act: 5.1019. Min Act: -0.1700
Data Index: 2042726 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6957. Min Range: -5.6957
Max Act: 5.1019. Min Act: -0.1700
Data Index: 492331 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6957. Min Range: -5.6957
Max Act: 5.0707. Min Act: -0.1700
Data Index: 2109207 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19