Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4389 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3144. Min Range: -7.3144
Max Act: 7.3144. Min Act: -0.1700
Data Index: 5206133 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3144. Min Range: -7.3144
Max Act: 7.1894. Min Act: -0.1700
Data Index: 1471940 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3144. Min Range: -7.3144
Max Act: 7.1894. Min Act: -0.1700
Data Index: 6576668 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3144. Min Range: -7.3144
Max Act: 7.1894. Min Act: -0.1700
Data Index: 2402073 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3144. Min Range: -7.3144
Max Act: 7.1582. Min Act: -0.1700
Data Index: 5725193 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3144. Min Range: -7.3144
Max Act: 7.0957. Min Act: -0.1700
Data Index: 458021 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3144. Min Range: -7.3144
Max Act: 7.1269. Min Act: -0.1700
Data Index: 1334908 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3144. Min Range: -7.3144
Max Act: 7.1269. Min Act: -0.1700
Data Index: 4382181 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3144. Min Range: -7.3144
Max Act: 7.1269. Min Act: -0.1700
Data Index: 6558994 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3144. Min Range: -7.3144
Max Act: 7.0644. Min Act: -0.1700
Data Index: 2869212 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3144. Min Range: -7.3144
Max Act: 7.0644. Min Act: -0.1700
Data Index: 1471939 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3144. Min Range: -7.3144
Max Act: 7.0644. Min Act: -0.1700
Data Index: 4220564 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3144. Min Range: -7.3144
Max Act: 7.0644. Min Act: -0.1700
Data Index: 6863384 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3144. Min Range: -7.3144
Max Act: 7.0332. Min Act: -0.1700
Data Index: 2163345 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3144. Min Range: -7.3144
Max Act: 7.0332. Min Act: -0.1700
Data Index: 4977626 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3144. Min Range: -7.3144
Max Act: 7.0332. Min Act: -0.1700
Data Index: 1496793 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3144. Min Range: -7.3144
Max Act: 7.0332. Min Act: -0.1700
Data Index: 4153158 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3144. Min Range: -7.3144
Max Act: 7.0332. Min Act: -0.1700
Data Index: 2639056 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3144. Min Range: -7.3144
Max Act: 7.0332. Min Act: -0.1700
Data Index: 5725194 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3144. Min Range: -7.3144
Max Act: 7.0332. Min Act: -0.1700
Data Index: 4888098 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19