Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3886 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8089. Min Range: -8.8089
Max Act: 8.8089. Min Act: -0.1700
Data Index: 2878142 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8089. Min Range: -8.8089
Max Act: 8.6214. Min Act: -0.1700
Data Index: 3443532 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8089. Min Range: -8.8089
Max Act: 8.5589. Min Act: -0.1700
Data Index: 7194830 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8089. Min Range: -8.8089
Max Act: 8.5589. Min Act: -0.1700
Data Index: 3673777 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8089. Min Range: -8.8089
Max Act: 8.4964. Min Act: -0.1700
Data Index: 6625651 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8089. Min Range: -8.8089
Max Act: 8.4964. Min Act: -0.1700
Data Index: 1288204 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8089. Min Range: -8.8089
Max Act: 8.4964. Min Act: -0.1700
Data Index: 3905470 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8089. Min Range: -8.8089
Max Act: 8.5589. Min Act: -0.1700
Data Index: 3614265 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8089. Min Range: -8.8089
Max Act: 8.4339. Min Act: -0.1700
Data Index: 7679248 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8089. Min Range: -8.8089
Max Act: 8.3714. Min Act: -0.1700
Data Index: 4273615 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8089. Min Range: -8.8089
Max Act: 8.4339. Min Act: -0.1700
Data Index: 1790148 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8089. Min Range: -8.8089
Max Act: 8.3089. Min Act: -0.1700
Data Index: 741170 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8089. Min Range: -8.8089
Max Act: 8.3089. Min Act: -0.1700
Data Index: 8352146 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8089. Min Range: -8.8089
Max Act: 8.3089. Min Act: -0.1700
Data Index: 362705 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8089. Min Range: -8.8089
Max Act: 8.3089. Min Act: -0.1700
Data Index: 3085885 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8089. Min Range: -8.8089
Max Act: 8.1839. Min Act: -0.1700
Data Index: 8097805 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8089. Min Range: -8.8089
Max Act: 8.1839. Min Act: -0.1700
Data Index: 7653702 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8089. Min Range: -8.8089
Max Act: 8.1839. Min Act: -0.1700
Data Index: 4346530 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8089. Min Range: -8.8089
Max Act: 8.1214. Min Act: -0.1700
Data Index: 1513542 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8089. Min Range: -8.8089
Max Act: 8.1839. Min Act: -0.1700
Data Index: 1569647 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19