Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2916 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.5957. Min Act: -0.1700
Data Index: 2934386 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.5645. Min Act: -0.1700
Data Index: 4307986 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.5332. Min Act: -0.1700
Data Index: 2338854 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.5332. Min Act: -0.1700
Data Index: 3863789 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.5020. Min Act: -0.1700
Data Index: 2939205 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.5020. Min Act: -0.1700
Data Index: 1393727 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.5020. Min Act: -0.1700
Data Index: 7598989 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.4707. Min Act: -0.1700
Data Index: 7636480 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.5020. Min Act: -0.1700
Data Index: 7769028 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.4707. Min Act: -0.1700
Data Index: 5235390 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.4707. Min Act: -0.1700
Data Index: 2024695 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.4707. Min Act: -0.1700
Data Index: 2516563 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.4395. Min Act: -0.1700
Data Index: 4981680 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.4395. Min Act: -0.1700
Data Index: 8759503 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.4082. Min Act: -0.1700
Data Index: 8634849 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.4082. Min Act: -0.1700
Data Index: 1633154 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.4395. Min Act: -0.1700
Data Index: 6469080 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.4395. Min Act: -0.1700
Data Index: 3220179 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.4082. Min Act: -0.1700
Data Index: 965911 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.4082. Min Act: -0.1700
Data Index: 4743162 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19