Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3094 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2482. Min Range: -6.2482
Max Act: 6.2482. Min Act: -0.1700
Data Index: 1139176 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2482. Min Range: -6.2482
Max Act: 6.1232. Min Act: -0.1700
Data Index: 1105864 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2482. Min Range: -6.2482
Max Act: 6.0919. Min Act: -0.1700
Data Index: 5091345 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2482. Min Range: -6.2482
Max Act: 6.0919. Min Act: -0.1700
Data Index: 484981 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2482. Min Range: -6.2482
Max Act: 5.9357. Min Act: -0.1700
Data Index: 8039235 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2482. Min Range: -6.2482
Max Act: 5.9044. Min Act: -0.1700
Data Index: 1669456 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2482. Min Range: -6.2482
Max Act: 5.9044. Min Act: -0.1700
Data Index: 6019919 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2482. Min Range: -6.2482
Max Act: 5.8732. Min Act: -0.1700
Data Index: 5870896 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2482. Min Range: -6.2482
Max Act: 5.8419. Min Act: -0.1700
Data Index: 4967572 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2482. Min Range: -6.2482
Max Act: 5.8419. Min Act: -0.1700
Data Index: 7308257 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2482. Min Range: -6.2482
Max Act: 5.8107. Min Act: -0.1700
Data Index: 3654945 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2482. Min Range: -6.2482
Max Act: 5.8107. Min Act: -0.1700
Data Index: 5188072 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2482. Min Range: -6.2482
Max Act: 5.8107. Min Act: -0.1700
Data Index: 6623587 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2482. Min Range: -6.2482
Max Act: 5.7794. Min Act: -0.1700
Data Index: 6960050 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2482. Min Range: -6.2482
Max Act: 5.7794. Min Act: -0.1700
Data Index: 2140075 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2482. Min Range: -6.2482
Max Act: 5.7794. Min Act: -0.1700
Data Index: 3843071 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2482. Min Range: -6.2482
Max Act: 5.7794. Min Act: -0.1700
Data Index: 1888501 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2482. Min Range: -6.2482
Max Act: 5.7482. Min Act: -0.1700
Data Index: 2466564 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2482. Min Range: -6.2482
Max Act: 5.7482. Min Act: -0.1700
Data Index: 8217052 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2482. Min Range: -6.2482
Max Act: 5.7482. Min Act: -0.1700
Data Index: 6577976 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19