Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3040 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0370. Min Range: -7.0370
Max Act: 7.0370. Min Act: -0.1700
Data Index: 4426941 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0370. Min Range: -7.0370
Max Act: 6.9120. Min Act: -0.1700
Data Index: 7457761 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0370. Min Range: -7.0370
Max Act: 6.7558. Min Act: -0.1700
Data Index: 4426940 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0370. Min Range: -7.0370
Max Act: 6.5995. Min Act: -0.1700
Data Index: 3450322 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0370. Min Range: -7.0370
Max Act: 6.5683. Min Act: -0.1700
Data Index: 8748279 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0370. Min Range: -7.0370
Max Act: 6.3183. Min Act: -0.1700
Data Index: 2193270 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0370. Min Range: -7.0370
Max Act: 6.3183. Min Act: -0.1700
Data Index: 3910753 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0370. Min Range: -7.0370
Max Act: 6.2558. Min Act: -0.1700
Data Index: 8775160 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0370. Min Range: -7.0370
Max Act: 6.2245. Min Act: -0.1700
Data Index: 695267 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0370. Min Range: -7.0370
Max Act: 6.1933. Min Act: -0.1700
Data Index: 1869125 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0370. Min Range: -7.0370
Max Act: 6.1308. Min Act: -0.1700
Data Index: 5990151 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0370. Min Range: -7.0370
Max Act: 6.1308. Min Act: -0.1700
Data Index: 7901291 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0370. Min Range: -7.0370
Max Act: 6.0995. Min Act: -0.1700
Data Index: 1672223 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0370. Min Range: -7.0370
Max Act: 6.0683. Min Act: -0.1700
Data Index: 2387328 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0370. Min Range: -7.0370
Max Act: 6.0995. Min Act: -0.1700
Data Index: 4050614 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0370. Min Range: -7.0370
Max Act: 6.0683. Min Act: -0.1700
Data Index: 4402886 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0370. Min Range: -7.0370
Max Act: 6.0683. Min Act: -0.1700
Data Index: 3210395 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0370. Min Range: -7.0370
Max Act: 6.0683. Min Act: -0.1700
Data Index: 5349799 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0370. Min Range: -7.0370
Max Act: 6.0370. Min Act: -0.1700
Data Index: 103534 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0370. Min Range: -7.0370
Max Act: 6.0370. Min Act: -0.1700
Data Index: 2172095 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #19