Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2874 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6138. Min Range: -6.6138
Max Act: 6.6138. Min Act: -0.1700
Data Index: 7461487 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6138. Min Range: -6.6138
Max Act: 6.4888. Min Act: -0.1700
Data Index: 2315690 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6138. Min Range: -6.6138
Max Act: 6.4888. Min Act: -0.1700
Data Index: 5846662 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6138. Min Range: -6.6138
Max Act: 6.3951. Min Act: -0.1700
Data Index: 144614 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6138. Min Range: -6.6138
Max Act: 6.3951. Min Act: -0.1700
Data Index: 1483286 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6138. Min Range: -6.6138
Max Act: 6.3951. Min Act: -0.1700
Data Index: 7887861 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6138. Min Range: -6.6138
Max Act: 6.3638. Min Act: -0.1700
Data Index: 4490953 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6138. Min Range: -6.6138
Max Act: 6.3638. Min Act: -0.1700
Data Index: 7757671 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6138. Min Range: -6.6138
Max Act: 6.3638. Min Act: -0.1700
Data Index: 7350103 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6138. Min Range: -6.6138
Max Act: 6.3638. Min Act: -0.1700
Data Index: 4515327 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6138. Min Range: -6.6138
Max Act: 6.3638. Min Act: -0.1700
Data Index: 2312129 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6138. Min Range: -6.6138
Max Act: 6.3326. Min Act: -0.1700
Data Index: 8134910 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6138. Min Range: -6.6138
Max Act: 6.3326. Min Act: -0.1700
Data Index: 8798323 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6138. Min Range: -6.6138
Max Act: 6.3013. Min Act: -0.1700
Data Index: 8291210 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6138. Min Range: -6.6138
Max Act: 6.3013. Min Act: -0.1700
Data Index: 249086 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6138. Min Range: -6.6138
Max Act: 6.3013. Min Act: -0.1700
Data Index: 5844872 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6138. Min Range: -6.6138
Max Act: 6.2701. Min Act: -0.1700
Data Index: 6697441 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6138. Min Range: -6.6138
Max Act: 6.2701. Min Act: -0.1700
Data Index: 520149 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6138. Min Range: -6.6138
Max Act: 6.2701. Min Act: -0.1700
Data Index: 6070310 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6138. Min Range: -6.6138
Max Act: 6.2701. Min Act: -0.1700
Data Index: 8773948 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19