Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 258 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8629. Min Range: -3.8629
Max Act: 3.8629. Min Act: -0.1700
Data Index: 3814779 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8629. Min Range: -3.8629
Max Act: 3.7534. Min Act: -0.1700
Data Index: 8259612 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8629. Min Range: -3.8629
Max Act: 3.7221. Min Act: -0.1700
Data Index: 6405164 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8629. Min Range: -3.8629
Max Act: 3.6439. Min Act: -0.1700
Data Index: 2815491 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8629. Min Range: -3.8629
Max Act: 3.5970. Min Act: -0.1700
Data Index: 1662804 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8629. Min Range: -3.8629
Max Act: 3.5813. Min Act: -0.1700
Data Index: 8517528 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8629. Min Range: -3.8629
Max Act: 3.5187. Min Act: -0.1700
Data Index: 1792711 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8629. Min Range: -3.8629
Max Act: 3.5030. Min Act: -0.1700
Data Index: 5013164 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8629. Min Range: -3.8629
Max Act: 3.5030. Min Act: -0.1700
Data Index: 7951120 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8629. Min Range: -3.8629
Max Act: 3.4873. Min Act: -0.1700
Data Index: 7145715 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8629. Min Range: -3.8629
Max Act: 3.4717. Min Act: -0.1700
Data Index: 3449521 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8629. Min Range: -3.8629
Max Act: 3.4873. Min Act: -0.1700
Data Index: 4763365 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8629. Min Range: -3.8629
Max Act: 3.4717. Min Act: -0.1700
Data Index: 1339764 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8629. Min Range: -3.8629
Max Act: 3.4560. Min Act: -0.1700
Data Index: 1232025 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8629. Min Range: -3.8629
Max Act: 3.4403. Min Act: -0.1700
Data Index: 6373728 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8629. Min Range: -3.8629
Max Act: 3.4403. Min Act: -0.1700
Data Index: 2000190 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8629. Min Range: -3.8629
Max Act: 3.4247. Min Act: -0.1700
Data Index: 7946603 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8629. Min Range: -3.8629
Max Act: 3.3933. Min Act: -0.1700
Data Index: 1624067 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8629. Min Range: -3.8629
Max Act: 3.4090. Min Act: -0.1700
Data Index: 4131295 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8629. Min Range: -3.8629
Max Act: 3.4090. Min Act: -0.1700
Data Index: 6265587 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19