Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1762 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2845. Min Range: -5.2845
Max Act: 5.2845. Min Act: -0.1700
Data Index: 303608 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2845. Min Range: -5.2845
Max Act: 5.2220. Min Act: -0.1700
Data Index: 303612 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2845. Min Range: -5.2845
Max Act: 5.2532. Min Act: -0.1700
Data Index: 3501304 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2845. Min Range: -5.2845
Max Act: 5.2532. Min Act: -0.1700
Data Index: 5064528 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2845. Min Range: -5.2845
Max Act: 5.2532. Min Act: -0.1700
Data Index: 3501308 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2845. Min Range: -5.2845
Max Act: 5.2220. Min Act: -0.1700
Data Index: 4843288 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2845. Min Range: -5.2845
Max Act: 5.1907. Min Act: -0.1700
Data Index: 3796888 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2845. Min Range: -5.2845
Max Act: 5.1907. Min Act: -0.1700
Data Index: 6792618 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2845. Min Range: -5.2845
Max Act: 5.1595. Min Act: -0.1700
Data Index: 5189014 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2845. Min Range: -5.2845
Max Act: 5.1595. Min Act: -0.1700
Data Index: 377677 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2845. Min Range: -5.2845
Max Act: 5.1595. Min Act: -0.1700
Data Index: 8560795 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2845. Min Range: -5.2845
Max Act: 5.1907. Min Act: -0.1700
Data Index: 3881977 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2845. Min Range: -5.2845
Max Act: 5.1595. Min Act: -0.1700
Data Index: 4457729 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2845. Min Range: -5.2845
Max Act: 5.1595. Min Act: -0.1700
Data Index: 5676427 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2845. Min Range: -5.2845
Max Act: 5.1595. Min Act: -0.1700
Data Index: 3796893 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2845. Min Range: -5.2845
Max Act: 5.1595. Min Act: -0.1700
Data Index: 6765472 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2845. Min Range: -5.2845
Max Act: 5.1282. Min Act: -0.1700
Data Index: 6765477 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2845. Min Range: -5.2845
Max Act: 5.1595. Min Act: -0.1700
Data Index: 1627920 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2845. Min Range: -5.2845
Max Act: 5.0970. Min Act: -0.1700
Data Index: 377656 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2845. Min Range: -5.2845
Max Act: 5.1595. Min Act: -0.1700
Data Index: 8560807 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19