Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2877 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8946. Min Range: -4.8946
Max Act: 4.8946. Min Act: -0.1700
Data Index: 402592 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8946. Min Range: -4.8946
Max Act: 4.8634. Min Act: -0.1700
Data Index: 7791989 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8946. Min Range: -4.8946
Max Act: 4.5509. Min Act: -0.1700
Data Index: 3790911 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8946. Min Range: -4.8946
Max Act: 4.5196. Min Act: -0.1700
Data Index: 58287 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8946. Min Range: -4.8946
Max Act: 4.4884. Min Act: -0.1700
Data Index: 2794922 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8946. Min Range: -4.8946
Max Act: 4.4571. Min Act: -0.1700
Data Index: 865086 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8946. Min Range: -4.8946
Max Act: 4.4259. Min Act: -0.1700
Data Index: 7424009 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8946. Min Range: -4.8946
Max Act: 4.4571. Min Act: -0.1700
Data Index: 3773311 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8946. Min Range: -4.8946
Max Act: 4.3946. Min Act: -0.1700
Data Index: 25709 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8946. Min Range: -4.8946
Max Act: 4.3634. Min Act: -0.1700
Data Index: 2396661 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8946. Min Range: -4.8946
Max Act: 4.3634. Min Act: -0.1700
Data Index: 1666701 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8946. Min Range: -4.8946
Max Act: 4.3634. Min Act: -0.1700
Data Index: 3798229 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8946. Min Range: -4.8946
Max Act: 4.3321. Min Act: -0.1700
Data Index: 6335496 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8946. Min Range: -4.8946
Max Act: 4.3321. Min Act: -0.1700
Data Index: 2297843 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8946. Min Range: -4.8946
Max Act: 4.3634. Min Act: -0.1700
Data Index: 1762381 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8946. Min Range: -4.8946
Max Act: 4.3321. Min Act: -0.1700
Data Index: 629739 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8946. Min Range: -4.8946
Max Act: 4.3321. Min Act: -0.1700
Data Index: 1312612 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8946. Min Range: -4.8946
Max Act: 4.3009. Min Act: -0.1700
Data Index: 7674698 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8946. Min Range: -4.8946
Max Act: 4.3009. Min Act: -0.1700
Data Index: 6659002 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8946. Min Range: -4.8946
Max Act: 4.2384. Min Act: -0.1700
Data Index: 5048981 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #19