Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2553 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.7043. Min Act: -0.1700
Data Index: 3169614 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.6105. Min Act: -0.1700
Data Index: 2899198 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5793. Min Act: -0.1700
Data Index: 8501415 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5793. Min Act: -0.1700
Data Index: 6543501 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5168. Min Act: -0.1700
Data Index: 5323210 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5168. Min Act: -0.1700
Data Index: 1441479 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.4855. Min Act: -0.1700
Data Index: 6622510 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.4543. Min Act: -0.1700
Data Index: 8486417 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.4855. Min Act: -0.1700
Data Index: 1429735 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.4855. Min Act: -0.1700
Data Index: 5761327 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.4543. Min Act: -0.1700
Data Index: 55168 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.4543. Min Act: -0.1700
Data Index: 4736546 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.3918. Min Act: -0.1700
Data Index: 7277929 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.3918. Min Act: -0.1700
Data Index: 4828510 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.4230. Min Act: -0.1700
Data Index: 3865355 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.3918. Min Act: -0.1700
Data Index: 882055 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.3918. Min Act: -0.1700
Data Index: 8645107 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.3918. Min Act: -0.1700
Data Index: 4185620 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.3293. Min Act: -0.1700
Data Index: 7479846 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.3293. Min Act: -0.1700
Data Index: 2836372 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19