Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2955 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3685. Min Range: -5.3685
Max Act: 5.3685. Min Act: -0.1700
Data Index: 4678506 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3685. Min Range: -5.3685
Max Act: 5.3373. Min Act: -0.1700
Data Index: 8440826 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3685. Min Range: -5.3685
Max Act: 5.2123. Min Act: -0.1700
Data Index: 8352105 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3685. Min Range: -5.3685
Max Act: 5.1810. Min Act: -0.1700
Data Index: 2455879 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3685. Min Range: -5.3685
Max Act: 5.1498. Min Act: -0.1700
Data Index: 7270430 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3685. Min Range: -5.3685
Max Act: 5.1185. Min Act: -0.1700
Data Index: 1154165 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3685. Min Range: -5.3685
Max Act: 5.1185. Min Act: -0.1700
Data Index: 667964 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3685. Min Range: -5.3685
Max Act: 5.1185. Min Act: -0.1700
Data Index: 8686332 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3685. Min Range: -5.3685
Max Act: 5.1185. Min Act: -0.1700
Data Index: 8499522 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3685. Min Range: -5.3685
Max Act: 5.0560. Min Act: -0.1700
Data Index: 8409409 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3685. Min Range: -5.3685
Max Act: 5.0560. Min Act: -0.1700
Data Index: 1557946 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3685. Min Range: -5.3685
Max Act: 5.0248. Min Act: -0.1700
Data Index: 6617697 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3685. Min Range: -5.3685
Max Act: 5.0248. Min Act: -0.1700
Data Index: 2457078 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3685. Min Range: -5.3685
Max Act: 4.9623. Min Act: -0.1700
Data Index: 5448537 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3685. Min Range: -5.3685
Max Act: 4.9623. Min Act: -0.1700
Data Index: 4191892 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3685. Min Range: -5.3685
Max Act: 4.9935. Min Act: -0.1700
Data Index: 247798 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3685. Min Range: -5.3685
Max Act: 4.9935. Min Act: -0.1700
Data Index: 7798745 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3685. Min Range: -5.3685
Max Act: 4.9310. Min Act: -0.1700
Data Index: 812515 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3685. Min Range: -5.3685
Max Act: 4.9310. Min Act: -0.1700
Data Index: 2249887 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3685. Min Range: -5.3685
Max Act: 4.9623. Min Act: -0.1700
Data Index: 5115375 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19