Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3085 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6801. Min Range: -5.6801
Max Act: 5.6801. Min Act: -0.1700
Data Index: 3632014 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6801. Min Range: -5.6801
Max Act: 5.6176. Min Act: -0.1700
Data Index: 721485 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6801. Min Range: -5.6801
Max Act: 5.6489. Min Act: -0.1700
Data Index: 5593322 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6801. Min Range: -5.6801
Max Act: 5.6176. Min Act: -0.1700
Data Index: 5610232 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6801. Min Range: -5.6801
Max Act: 5.5864. Min Act: -0.1700
Data Index: 7831566 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6801. Min Range: -5.6801
Max Act: 5.5864. Min Act: -0.1700
Data Index: 4940480 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6801. Min Range: -5.6801
Max Act: 5.5551. Min Act: -0.1700
Data Index: 8736300 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6801. Min Range: -5.6801
Max Act: 5.5239. Min Act: -0.1700
Data Index: 4992057 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6801. Min Range: -5.6801
Max Act: 5.4926. Min Act: -0.1700
Data Index: 630910 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6801. Min Range: -5.6801
Max Act: 5.4926. Min Act: -0.1700
Data Index: 6962922 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6801. Min Range: -5.6801
Max Act: 5.4926. Min Act: -0.1700
Data Index: 5742345 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6801. Min Range: -5.6801
Max Act: 5.5239. Min Act: -0.1700
Data Index: 4490392 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6801. Min Range: -5.6801
Max Act: 5.4614. Min Act: -0.1700
Data Index: 6260618 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6801. Min Range: -5.6801
Max Act: 5.4614. Min Act: -0.1700
Data Index: 5610234 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6801. Min Range: -5.6801
Max Act: 5.4301. Min Act: -0.1700
Data Index: 6066721 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6801. Min Range: -5.6801
Max Act: 5.4301. Min Act: -0.1700
Data Index: 2640742 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6801. Min Range: -5.6801
Max Act: 5.4301. Min Act: -0.1700
Data Index: 8106063 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6801. Min Range: -5.6801
Max Act: 5.3989. Min Act: -0.1700
Data Index: 3707064 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6801. Min Range: -5.6801
Max Act: 5.3989. Min Act: -0.1700
Data Index: 5631466 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6801. Min Range: -5.6801
Max Act: 5.3989. Min Act: -0.1700
Data Index: 6008714 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #19