Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2508 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.1960. Min Range: -8.1960
Max Act: 8.1960. Min Act: -0.1700
Data Index: 1908966 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1960. Min Range: -8.1960
Max Act: 8.1335. Min Act: -0.1700
Data Index: 1744325 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1960. Min Range: -8.1960
Max Act: 7.8210. Min Act: -0.1700
Data Index: 5063 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1960. Min Range: -8.1960
Max Act: 7.8210. Min Act: -0.1700
Data Index: 6352555 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1960. Min Range: -8.1960
Max Act: 7.8210. Min Act: -0.1700
Data Index: 7279635 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1960. Min Range: -8.1960
Max Act: 7.8210. Min Act: -0.1700
Data Index: 5699182 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1960. Min Range: -8.1960
Max Act: 7.7897. Min Act: -0.1700
Data Index: 3494165 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1960. Min Range: -8.1960
Max Act: 7.7585. Min Act: -0.1700
Data Index: 5817011 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1960. Min Range: -8.1960
Max Act: 7.7272. Min Act: -0.1700
Data Index: 3539096 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1960. Min Range: -8.1960
Max Act: 7.6960. Min Act: -0.1700
Data Index: 8308167 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1960. Min Range: -8.1960
Max Act: 7.6647. Min Act: -0.1700
Data Index: 901634 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1960. Min Range: -8.1960
Max Act: 7.6960. Min Act: -0.1700
Data Index: 5162822 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1960. Min Range: -8.1960
Max Act: 7.6335. Min Act: -0.1700
Data Index: 1265340 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1960. Min Range: -8.1960
Max Act: 7.6647. Min Act: -0.1700
Data Index: 5754296 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1960. Min Range: -8.1960
Max Act: 7.6647. Min Act: -0.1700
Data Index: 8200410 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1960. Min Range: -8.1960
Max Act: 7.6335. Min Act: -0.1700
Data Index: 1337778 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1960. Min Range: -8.1960
Max Act: 7.5710. Min Act: -0.1700
Data Index: 7687583 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1960. Min Range: -8.1960
Max Act: 7.5710. Min Act: -0.1700
Data Index: 4703020 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1960. Min Range: -8.1960
Max Act: 7.5710. Min Act: -0.1700
Data Index: 4062918 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1960. Min Range: -8.1960
Max Act: 7.5710. Min Act: -0.1700
Data Index: 5094737 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19