Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2880 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3450. Min Range: -5.3450
Max Act: 5.3450. Min Act: -0.1700
Data Index: 889013 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3450. Min Range: -5.3450
Max Act: 5.3450. Min Act: -0.1700
Data Index: 7823479 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3450. Min Range: -5.3450
Max Act: 5.3137. Min Act: -0.1700
Data Index: 3533762 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3450. Min Range: -5.3450
Max Act: 5.3137. Min Act: -0.1700
Data Index: 7773394 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3450. Min Range: -5.3450
Max Act: 5.2825. Min Act: -0.1700
Data Index: 7276103 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3450. Min Range: -5.3450
Max Act: 5.2825. Min Act: -0.1700
Data Index: 8360630 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3450. Min Range: -5.3450
Max Act: 5.2200. Min Act: -0.1700
Data Index: 2988279 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3450. Min Range: -5.3450
Max Act: 5.2200. Min Act: -0.1700
Data Index: 3588433 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3450. Min Range: -5.3450
Max Act: 5.2200. Min Act: -0.1700
Data Index: 1904351 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3450. Min Range: -5.3450
Max Act: 5.2200. Min Act: -0.1700
Data Index: 6532549 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3450. Min Range: -5.3450
Max Act: 5.2200. Min Act: -0.1700
Data Index: 212054 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3450. Min Range: -5.3450
Max Act: 5.1887. Min Act: -0.1700
Data Index: 8621687 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3450. Min Range: -5.3450
Max Act: 5.1887. Min Act: -0.1700
Data Index: 1208003 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3450. Min Range: -5.3450
Max Act: 5.1887. Min Act: -0.1700
Data Index: 2469043 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3450. Min Range: -5.3450
Max Act: 5.1887. Min Act: -0.1700
Data Index: 1758791 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3450. Min Range: -5.3450
Max Act: 5.1887. Min Act: -0.1700
Data Index: 8365529 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3450. Min Range: -5.3450
Max Act: 5.1887. Min Act: -0.1700
Data Index: 4496125 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3450. Min Range: -5.3450
Max Act: 5.1887. Min Act: -0.1700
Data Index: 4366931 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3450. Min Range: -5.3450
Max Act: 5.1887. Min Act: -0.1700
Data Index: 271158 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3450. Min Range: -5.3450
Max Act: 5.1887. Min Act: -0.1700
Data Index: 3552161 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19