Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3468 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3907. Min Range: -5.3907
Max Act: 5.3907. Min Act: -0.1700
Data Index: 3798087 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3907. Min Range: -5.3907
Max Act: 5.2345. Min Act: -0.1700
Data Index: 392777 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3907. Min Range: -5.3907
Max Act: 5.0782. Min Act: -0.1700
Data Index: 7660215 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3907. Min Range: -5.3907
Max Act: 4.9220. Min Act: -0.1700
Data Index: 4436385 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3907. Min Range: -5.3907
Max Act: 4.8907. Min Act: -0.1700
Data Index: 5598778 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3907. Min Range: -5.3907
Max Act: 4.8282. Min Act: -0.1700
Data Index: 332087 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3907. Min Range: -5.3907
Max Act: 4.8595. Min Act: -0.1700
Data Index: 206438 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3907. Min Range: -5.3907
Max Act: 4.8907. Min Act: -0.1700
Data Index: 2744392 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3907. Min Range: -5.3907
Max Act: 4.8282. Min Act: -0.1700
Data Index: 547032 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3907. Min Range: -5.3907
Max Act: 4.8595. Min Act: -0.1700
Data Index: 7070161 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3907. Min Range: -5.3907
Max Act: 4.8595. Min Act: -0.1700
Data Index: 1269581 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3907. Min Range: -5.3907
Max Act: 4.8282. Min Act: -0.1700
Data Index: 4740650 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3907. Min Range: -5.3907
Max Act: 4.8282. Min Act: -0.1700
Data Index: 7151482 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3907. Min Range: -5.3907
Max Act: 4.8282. Min Act: -0.1700
Data Index: 4471174 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3907. Min Range: -5.3907
Max Act: 4.7970. Min Act: -0.1700
Data Index: 5521759 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3907. Min Range: -5.3907
Max Act: 4.8595. Min Act: -0.1700
Data Index: 8281300 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3907. Min Range: -5.3907
Max Act: 4.7970. Min Act: -0.1700
Data Index: 5572935 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3907. Min Range: -5.3907
Max Act: 4.7970. Min Act: -0.1700
Data Index: 5040850 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3907. Min Range: -5.3907
Max Act: 4.7970. Min Act: -0.1700
Data Index: 5401280 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3907. Min Range: -5.3907
Max Act: 4.7970. Min Act: -0.1700
Data Index: 5343100 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19