Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4413 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.2066. Min Range: -8.2066
Max Act: 8.2066. Min Act: -0.1700
Data Index: 4647568 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2066. Min Range: -8.2066
Max Act: 7.7066. Min Act: -0.1700
Data Index: 4628701 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2066. Min Range: -8.2066
Max Act: 7.3629. Min Act: -0.1700
Data Index: 4722355 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2066. Min Range: -8.2066
Max Act: 7.3316. Min Act: -0.1700
Data Index: 2091685 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2066. Min Range: -8.2066
Max Act: 7.3316. Min Act: -0.1700
Data Index: 2825723 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2066. Min Range: -8.2066
Max Act: 7.2691. Min Act: -0.1700
Data Index: 6350818 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2066. Min Range: -8.2066
Max Act: 7.2379. Min Act: -0.1700
Data Index: 2111745 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2066. Min Range: -8.2066
Max Act: 7.2066. Min Act: -0.1700
Data Index: 5194929 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2066. Min Range: -8.2066
Max Act: 7.1754. Min Act: -0.1700
Data Index: 8546732 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2066. Min Range: -8.2066
Max Act: 7.2066. Min Act: -0.1700
Data Index: 8342370 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2066. Min Range: -8.2066
Max Act: 7.1754. Min Act: -0.1700
Data Index: 4257330 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2066. Min Range: -8.2066
Max Act: 7.0816. Min Act: -0.1700
Data Index: 444125 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2066. Min Range: -8.2066
Max Act: 7.0816. Min Act: -0.1700
Data Index: 8477214 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2066. Min Range: -8.2066
Max Act: 7.0816. Min Act: -0.1700
Data Index: 762986 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2066. Min Range: -8.2066
Max Act: 7.0816. Min Act: -0.1700
Data Index: 7447437 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2066. Min Range: -8.2066
Max Act: 7.0504. Min Act: -0.1700
Data Index: 5302848 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2066. Min Range: -8.2066
Max Act: 7.0504. Min Act: -0.1700
Data Index: 5513865 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2066. Min Range: -8.2066
Max Act: 7.0504. Min Act: -0.1700
Data Index: 3944573 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2066. Min Range: -8.2066
Max Act: 7.0191. Min Act: -0.1700
Data Index: 4137969 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2066. Min Range: -8.2066
Max Act: 6.9879. Min Act: -0.1700
Data Index: 5846856 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19