Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3358 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4973. Min Range: -5.4973
Max Act: 5.4973. Min Act: -0.1700
Data Index: 2931173 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4973. Min Range: -5.4973
Max Act: 5.3411. Min Act: -0.1700
Data Index: 383403 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4973. Min Range: -5.4973
Max Act: 5.3411. Min Act: -0.1700
Data Index: 2082337 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4973. Min Range: -5.4973
Max Act: 5.2786. Min Act: -0.1700
Data Index: 1802252 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4973. Min Range: -5.4973
Max Act: 5.2786. Min Act: -0.1700
Data Index: 5360284 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4973. Min Range: -5.4973
Max Act: 5.2786. Min Act: -0.1700
Data Index: 6749708 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4973. Min Range: -5.4973
Max Act: 5.2161. Min Act: -0.1700
Data Index: 3382261 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4973. Min Range: -5.4973
Max Act: 5.1848. Min Act: -0.1700
Data Index: 6229043 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4973. Min Range: -5.4973
Max Act: 5.1848. Min Act: -0.1700
Data Index: 8287464 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4973. Min Range: -5.4973
Max Act: 5.1848. Min Act: -0.1700
Data Index: 4826693 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4973. Min Range: -5.4973
Max Act: 5.1536. Min Act: -0.1700
Data Index: 6789286 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4973. Min Range: -5.4973
Max Act: 5.1536. Min Act: -0.1700
Data Index: 7522335 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4973. Min Range: -5.4973
Max Act: 5.1536. Min Act: -0.1700
Data Index: 3361780 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4973. Min Range: -5.4973
Max Act: 5.1536. Min Act: -0.1700
Data Index: 8365172 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4973. Min Range: -5.4973
Max Act: 5.1223. Min Act: -0.1700
Data Index: 2627210 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4973. Min Range: -5.4973
Max Act: 5.1223. Min Act: -0.1700
Data Index: 1041527 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4973. Min Range: -5.4973
Max Act: 5.1223. Min Act: -0.1700
Data Index: 6502526 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4973. Min Range: -5.4973
Max Act: 5.1223. Min Act: -0.1700
Data Index: 1910930 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4973. Min Range: -5.4973
Max Act: 5.1223. Min Act: -0.1700
Data Index: 5626139 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4973. Min Range: -5.4973
Max Act: 5.0911. Min Act: -0.1700
Data Index: 3098575 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #19