Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1958 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2123. Min Range: -9.2123
Max Act: 9.2123. Min Act: -0.1700
Data Index: 6291276 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2123. Min Range: -9.2123
Max Act: 9.1498. Min Act: -0.1700
Data Index: 4534413 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2123. Min Range: -9.2123
Max Act: 8.7748. Min Act: -0.1700
Data Index: 688543 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2123. Min Range: -9.2123
Max Act: 8.7123. Min Act: -0.1700
Data Index: 8139914 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2123. Min Range: -9.2123
Max Act: 8.5873. Min Act: -0.1700
Data Index: 2756620 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2123. Min Range: -9.2123
Max Act: 8.5873. Min Act: -0.1700
Data Index: 4159370 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2123. Min Range: -9.2123
Max Act: 8.5873. Min Act: -0.1700
Data Index: 985188 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2123. Min Range: -9.2123
Max Act: 8.3998. Min Act: -0.1700
Data Index: 4360857 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2123. Min Range: -9.2123
Max Act: 8.3373. Min Act: -0.1700
Data Index: 8332042 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2123. Min Range: -9.2123
Max Act: 8.2748. Min Act: -0.1700
Data Index: 4034309 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2123. Min Range: -9.2123
Max Act: 8.2123. Min Act: -0.1700
Data Index: 8529126 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2123. Min Range: -9.2123
Max Act: 8.2123. Min Act: -0.1700
Data Index: 4249887 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2123. Min Range: -9.2123
Max Act: 8.1810. Min Act: -0.1700
Data Index: 2712472 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2123. Min Range: -9.2123
Max Act: 8.1498. Min Act: -0.1700
Data Index: 519960 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2123. Min Range: -9.2123
Max Act: 8.1185. Min Act: -0.1700
Data Index: 2255265 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2123. Min Range: -9.2123
Max Act: 8.0873. Min Act: -0.1700
Data Index: 2787747 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2123. Min Range: -9.2123
Max Act: 8.0873. Min Act: -0.1700
Data Index: 3222414 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2123. Min Range: -9.2123
Max Act: 8.0560. Min Act: -0.1700
Data Index: 2787746 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2123. Min Range: -9.2123
Max Act: 8.0248. Min Act: -0.1700
Data Index: 1334342 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2123. Min Range: -9.2123
Max Act: 7.9935. Min Act: -0.1700
Data Index: 7464885 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19