Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1822 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0717. Min Range: -5.0717
Max Act: 5.0717. Min Act: -0.1700
Data Index: 1387370 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0717. Min Range: -5.0717
Max Act: 4.8217. Min Act: -0.1700
Data Index: 7079764 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0717. Min Range: -5.0717
Max Act: 4.8217. Min Act: -0.1700
Data Index: 255141 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0717. Min Range: -5.0717
Max Act: 4.6967. Min Act: -0.1700
Data Index: 320026 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0717. Min Range: -5.0717
Max Act: 4.5717. Min Act: -0.1700
Data Index: 7772000 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0717. Min Range: -5.0717
Max Act: 4.5404. Min Act: -0.1700
Data Index: 3480671 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0717. Min Range: -5.0717
Max Act: 4.4779. Min Act: -0.1700
Data Index: 8450108 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0717. Min Range: -5.0717
Max Act: 4.4779. Min Act: -0.1700
Data Index: 4458995 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0717. Min Range: -5.0717
Max Act: 4.4467. Min Act: -0.1700
Data Index: 978880 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0717. Min Range: -5.0717
Max Act: 4.4154. Min Act: -0.1700
Data Index: 7148372 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0717. Min Range: -5.0717
Max Act: 4.4467. Min Act: -0.1700
Data Index: 7340985 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0717. Min Range: -5.0717
Max Act: 4.4154. Min Act: -0.1700
Data Index: 661678 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0717. Min Range: -5.0717
Max Act: 4.4154. Min Act: -0.1700
Data Index: 527017 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0717. Min Range: -5.0717
Max Act: 4.4154. Min Act: -0.1700
Data Index: 5856855 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0717. Min Range: -5.0717
Max Act: 4.3842. Min Act: -0.1700
Data Index: 5352770 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0717. Min Range: -5.0717
Max Act: 4.4154. Min Act: -0.1700
Data Index: 3240975 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0717. Min Range: -5.0717
Max Act: 4.3529. Min Act: -0.1700
Data Index: 4546183 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0717. Min Range: -5.0717
Max Act: 4.3216. Min Act: -0.1700
Data Index: 6603907 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0717. Min Range: -5.0717
Max Act: 4.3216. Min Act: -0.1700
Data Index: 1305439 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0717. Min Range: -5.0717
Max Act: 4.2904. Min Act: -0.1700
Data Index: 1825170 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19