Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1411 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8988. Min Range: -7.8988
Max Act: 7.8988. Min Act: -0.1700
Data Index: 5804206 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8988. Min Range: -7.8988
Max Act: 7.0238. Min Act: -0.1700
Data Index: 8261719 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8988. Min Range: -7.8988
Max Act: 6.8988. Min Act: -0.1700
Data Index: 5804205 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8988. Min Range: -7.8988
Max Act: 6.8051. Min Act: -0.1700
Data Index: 4437384 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8988. Min Range: -7.8988
Max Act: 6.6488. Min Act: -0.1700
Data Index: 5448544 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8988. Min Range: -7.8988
Max Act: 6.6488. Min Act: -0.1700
Data Index: 5448547 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8988. Min Range: -7.8988
Max Act: 6.4926. Min Act: -0.1700
Data Index: 7758708 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8988. Min Range: -7.8988
Max Act: 6.4613. Min Act: -0.1700
Data Index: 8605262 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8988. Min Range: -7.8988
Max Act: 6.4301. Min Act: -0.1700
Data Index: 2395058 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8988. Min Range: -7.8988
Max Act: 6.3676. Min Act: -0.1700
Data Index: 2253521 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8988. Min Range: -7.8988
Max Act: 6.3676. Min Act: -0.1700
Data Index: 158730 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8988. Min Range: -7.8988
Max Act: 6.3363. Min Act: -0.1700
Data Index: 5596701 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8988. Min Range: -7.8988
Max Act: 6.3363. Min Act: -0.1700
Data Index: 426381 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8988. Min Range: -7.8988
Max Act: 6.3051. Min Act: -0.1700
Data Index: 4066861 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8988. Min Range: -7.8988
Max Act: 6.2738. Min Act: -0.1700
Data Index: 855180 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8988. Min Range: -7.8988
Max Act: 6.2426. Min Act: -0.1700
Data Index: 426382 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8988. Min Range: -7.8988
Max Act: 6.2426. Min Act: -0.1700
Data Index: 5767025 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8988. Min Range: -7.8988
Max Act: 6.2426. Min Act: -0.1700
Data Index: 1817863 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8988. Min Range: -7.8988
Max Act: 6.2426. Min Act: -0.1700
Data Index: 7214157 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8988. Min Range: -7.8988
Max Act: 6.2113. Min Act: -0.1700
Data Index: 2690441 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #19