Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3646 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7935. Min Range: -4.7935
Max Act: 4.7935. Min Act: -0.1700
Data Index: 5539170 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7935. Min Range: -4.7935
Max Act: 4.6373. Min Act: -0.1700
Data Index: 1180665 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7935. Min Range: -4.7935
Max Act: 4.5123. Min Act: -0.1700
Data Index: 2900191 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7935. Min Range: -4.7935
Max Act: 4.4498. Min Act: -0.1700
Data Index: 3919271 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7935. Min Range: -4.7935
Max Act: 4.4185. Min Act: -0.1700
Data Index: 1417880 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7935. Min Range: -4.7935
Max Act: 4.4498. Min Act: -0.1700
Data Index: 5002184 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7935. Min Range: -4.7935
Max Act: 4.4498. Min Act: -0.1700
Data Index: 4714591 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7935. Min Range: -4.7935
Max Act: 4.4498. Min Act: -0.1700
Data Index: 3470422 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7935. Min Range: -4.7935
Max Act: 4.4185. Min Act: -0.1700
Data Index: 4667998 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7935. Min Range: -4.7935
Max Act: 4.4185. Min Act: -0.1700
Data Index: 913229 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7935. Min Range: -4.7935
Max Act: 4.4185. Min Act: -0.1700
Data Index: 4814551 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7935. Min Range: -4.7935
Max Act: 4.4498. Min Act: -0.1700
Data Index: 5306974 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7935. Min Range: -4.7935
Max Act: 4.3560. Min Act: -0.1700
Data Index: 6214255 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7935. Min Range: -4.7935
Max Act: 4.3873. Min Act: -0.1700
Data Index: 8182471 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7935. Min Range: -4.7935
Max Act: 4.3873. Min Act: -0.1700
Data Index: 4831466 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7935. Min Range: -4.7935
Max Act: 4.3873. Min Act: -0.1700
Data Index: 4763142 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7935. Min Range: -4.7935
Max Act: 4.3560. Min Act: -0.1700
Data Index: 3055933 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7935. Min Range: -4.7935
Max Act: 4.3873. Min Act: -0.1700
Data Index: 5568789 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7935. Min Range: -4.7935
Max Act: 4.3560. Min Act: -0.1700
Data Index: 1420279 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7935. Min Range: -4.7935
Max Act: 4.3560. Min Act: -0.1700
Data Index: 813945 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19