Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2615 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7731. Min Range: -4.7731
Max Act: 4.7731. Min Act: -0.1698
Data Index: 7813902 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7731. Min Range: -4.7731
Max Act: 4.7106. Min Act: -0.1700
Data Index: 8550891 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7731. Min Range: -4.7731
Max Act: 4.6481. Min Act: -0.1700
Data Index: 6972369 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7731. Min Range: -4.7731
Max Act: 4.6169. Min Act: -0.1700
Data Index: 1703956 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7731. Min Range: -4.7731
Max Act: 4.6169. Min Act: -0.1700
Data Index: 7136984 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7731. Min Range: -4.7731
Max Act: 4.5543. Min Act: -0.1700
Data Index: 3024732 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7731. Min Range: -4.7731
Max Act: 4.5543. Min Act: -0.1700
Data Index: 4441572 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7731. Min Range: -4.7731
Max Act: 4.5543. Min Act: -0.1700
Data Index: 3131407 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7731. Min Range: -4.7731
Max Act: 4.5856. Min Act: -0.1700
Data Index: 4753794 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7731. Min Range: -4.7731
Max Act: 4.4918. Min Act: -0.1700
Data Index: 6842211 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7731. Min Range: -4.7731
Max Act: 4.4606. Min Act: -0.1700
Data Index: 3581605 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7731. Min Range: -4.7731
Max Act: 4.4606. Min Act: -0.1700
Data Index: 4939421 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7731. Min Range: -4.7731
Max Act: 4.4293. Min Act: -0.1700
Data Index: 2411297 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7731. Min Range: -4.7731
Max Act: 4.4293. Min Act: -0.1700
Data Index: 3418500 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7731. Min Range: -4.7731
Max Act: 4.4293. Min Act: -0.1700
Data Index: 979470 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7731. Min Range: -4.7731
Max Act: 4.3981. Min Act: -0.1700
Data Index: 8517471 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7731. Min Range: -4.7731
Max Act: 4.3668. Min Act: -0.1700
Data Index: 4753792 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7731. Min Range: -4.7731
Max Act: 4.3981. Min Act: -0.1700
Data Index: 1323019 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7731. Min Range: -4.7731
Max Act: 4.3668. Min Act: -0.1700
Data Index: 2543136 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7731. Min Range: -4.7731
Max Act: 4.3356. Min Act: -0.1700
Data Index: 3532874 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19