Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2032 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4770. Min Range: -5.4770
Max Act: 5.4770. Min Act: -0.1700
Data Index: 5004724 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4770. Min Range: -5.4770
Max Act: 5.4457. Min Act: -0.1700
Data Index: 531067 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4770. Min Range: -5.4770
Max Act: 5.4457. Min Act: -0.1700
Data Index: 2455531 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4770. Min Range: -5.4770
Max Act: 5.3832. Min Act: -0.1700
Data Index: 2260292 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4770. Min Range: -5.4770
Max Act: 5.3832. Min Act: -0.1700
Data Index: 427517 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4770. Min Range: -5.4770
Max Act: 5.3520. Min Act: -0.1700
Data Index: 7368555 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4770. Min Range: -5.4770
Max Act: 5.3520. Min Act: -0.1700
Data Index: 3920521 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4770. Min Range: -5.4770
Max Act: 5.2582. Min Act: -0.1700
Data Index: 5971357 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4770. Min Range: -5.4770
Max Act: 5.1957. Min Act: -0.1700
Data Index: 4094246 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4770. Min Range: -5.4770
Max Act: 5.2270. Min Act: -0.1700
Data Index: 1648166 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4770. Min Range: -5.4770
Max Act: 5.2270. Min Act: -0.1700
Data Index: 7847276 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4770. Min Range: -5.4770
Max Act: 5.1957. Min Act: -0.1700
Data Index: 6332726 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4770. Min Range: -5.4770
Max Act: 5.1957. Min Act: -0.1700
Data Index: 2294297 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4770. Min Range: -5.4770
Max Act: 5.1957. Min Act: -0.1700
Data Index: 6150714 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4770. Min Range: -5.4770
Max Act: 5.1645. Min Act: -0.1700
Data Index: 1094124 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4770. Min Range: -5.4770
Max Act: 5.1645. Min Act: -0.1700
Data Index: 5729457 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4770. Min Range: -5.4770
Max Act: 5.1645. Min Act: -0.1700
Data Index: 4979921 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4770. Min Range: -5.4770
Max Act: 5.1332. Min Act: -0.1700
Data Index: 806341 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4770. Min Range: -5.4770
Max Act: 5.1332. Min Act: -0.1700
Data Index: 3202119 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4770. Min Range: -5.4770
Max Act: 5.1332. Min Act: -0.1700
Data Index: 6332724 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19