Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1456 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5539. Min Range: -3.5539
Max Act: 3.5539. Min Act: -0.1700
Data Index: 363950 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5539. Min Range: -3.5539
Max Act: 3.5382. Min Act: -0.1700
Data Index: 4342308 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5539. Min Range: -3.5539
Max Act: 3.4599. Min Act: -0.1700
Data Index: 1155592 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5539. Min Range: -3.5539
Max Act: 3.4442. Min Act: -0.1700
Data Index: 7490375 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5539. Min Range: -3.5539
Max Act: 3.4442. Min Act: -0.1700
Data Index: 6188969 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5539. Min Range: -3.5539
Max Act: 3.4286. Min Act: -0.1700
Data Index: 1614575 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5539. Min Range: -3.5539
Max Act: 3.4442. Min Act: -0.1700
Data Index: 2374152 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5539. Min Range: -3.5539
Max Act: 3.4129. Min Act: -0.1700
Data Index: 6907301 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5539. Min Range: -3.5539
Max Act: 3.4286. Min Act: -0.1700
Data Index: 7868353 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5539. Min Range: -3.5539
Max Act: 3.4286. Min Act: -0.1700
Data Index: 4300307 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5539. Min Range: -3.5539
Max Act: 3.4129. Min Act: -0.1700
Data Index: 6615907 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5539. Min Range: -3.5539
Max Act: 3.3815. Min Act: -0.1700
Data Index: 7868354 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5539. Min Range: -3.5539
Max Act: 3.3659. Min Act: -0.1700
Data Index: 5082212 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5539. Min Range: -3.5539
Max Act: 3.3502. Min Act: -0.1700
Data Index: 231265 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5539. Min Range: -3.5539
Max Act: 3.3345. Min Act: -0.1700
Data Index: 5223061 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5539. Min Range: -3.5539
Max Act: 3.3188. Min Act: -0.1700
Data Index: 4449194 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5539. Min Range: -3.5539
Max Act: 3.3188. Min Act: -0.1700
Data Index: 7467601 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5539. Min Range: -3.5539
Max Act: 3.3188. Min Act: -0.1700
Data Index: 8733852 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5539. Min Range: -3.5539
Max Act: 3.3031. Min Act: -0.1700
Data Index: 761115 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5539. Min Range: -3.5539
Max Act: 3.3188. Min Act: -0.1700
Data Index: 5837952 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19