Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2186 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8020. Min Range: -4.8020
Max Act: 4.8020. Min Act: -0.1700
Data Index: 78973 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8020. Min Range: -4.8020
Max Act: 4.7707. Min Act: -0.1700
Data Index: 944631 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8020. Min Range: -4.8020
Max Act: 4.6770. Min Act: -0.1700
Data Index: 3844768 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8020. Min Range: -4.8020
Max Act: 4.6457. Min Act: -0.1700
Data Index: 4082250 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8020. Min Range: -4.8020
Max Act: 4.6145. Min Act: -0.1700
Data Index: 4091605 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8020. Min Range: -4.8020
Max Act: 4.6145. Min Act: -0.1700
Data Index: 5227939 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8020. Min Range: -4.8020
Max Act: 4.6145. Min Act: -0.1700
Data Index: 8056448 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8020. Min Range: -4.8020
Max Act: 4.5832. Min Act: -0.1700
Data Index: 4262432 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8020. Min Range: -4.8020
Max Act: 4.5832. Min Act: -0.1700
Data Index: 3585852 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8020. Min Range: -4.8020
Max Act: 4.5520. Min Act: -0.1700
Data Index: 3056397 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8020. Min Range: -4.8020
Max Act: 4.5520. Min Act: -0.1700
Data Index: 1846343 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8020. Min Range: -4.8020
Max Act: 4.5520. Min Act: -0.1700
Data Index: 5370088 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8020. Min Range: -4.8020
Max Act: 4.5520. Min Act: -0.1700
Data Index: 6963902 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8020. Min Range: -4.8020
Max Act: 4.5207. Min Act: -0.1700
Data Index: 4796170 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8020. Min Range: -4.8020
Max Act: 4.5207. Min Act: -0.1700
Data Index: 1405150 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8020. Min Range: -4.8020
Max Act: 4.4895. Min Act: -0.1700
Data Index: 1332337 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8020. Min Range: -4.8020
Max Act: 4.4895. Min Act: -0.1700
Data Index: 2970342 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8020. Min Range: -4.8020
Max Act: 4.4895. Min Act: -0.1700
Data Index: 3392514 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8020. Min Range: -4.8020
Max Act: 4.4895. Min Act: -0.1700
Data Index: 3260970 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8020. Min Range: -4.8020
Max Act: 4.4582. Min Act: -0.1700
Data Index: 417494 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19