Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2389 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.9113. Min Act: -0.1700
Data Index: 6240149 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.5988. Min Act: -0.1700
Data Index: 5047348 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.5988. Min Act: -0.1700
Data Index: 5163190 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.5363. Min Act: -0.1700
Data Index: 1521721 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.5051. Min Act: -0.1700
Data Index: 398271 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.4738. Min Act: -0.1700
Data Index: 7847109 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.4738. Min Act: -0.1700
Data Index: 6002965 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.4738. Min Act: -0.1700
Data Index: 7569599 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.4426. Min Act: -0.1700
Data Index: 6731468 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.4113. Min Act: -0.1700
Data Index: 1083545 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.4113. Min Act: -0.1700
Data Index: 526671 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.4113. Min Act: -0.1700
Data Index: 3601344 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.3801. Min Act: -0.1700
Data Index: 567675 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.3801. Min Act: -0.1700
Data Index: 383433 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.3801. Min Act: -0.1700
Data Index: 5649726 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.3801. Min Act: -0.1700
Data Index: 1026473 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.3488. Min Act: -0.1700
Data Index: 2603302 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.3488. Min Act: -0.1700
Data Index: 1490672 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.3176. Min Act: -0.1700
Data Index: 5140832 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.3176. Min Act: -0.1700
Data Index: 5239333 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19