Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3887 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5360. Min Range: -5.5360
Max Act: 5.5360. Min Act: -0.1700
Data Index: 1999499 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5360. Min Range: -5.5360
Max Act: 5.2235. Min Act: -0.1700
Data Index: 672711 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5360. Min Range: -5.5360
Max Act: 5.1610. Min Act: -0.1700
Data Index: 6593167 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5360. Min Range: -5.5360
Max Act: 5.1298. Min Act: -0.1700
Data Index: 4599821 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5360. Min Range: -5.5360
Max Act: 5.1610. Min Act: -0.1700
Data Index: 2734159 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5360. Min Range: -5.5360
Max Act: 5.0985. Min Act: -0.1700
Data Index: 752300 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5360. Min Range: -5.5360
Max Act: 5.0360. Min Act: -0.1700
Data Index: 7692803 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5360. Min Range: -5.5360
Max Act: 5.0048. Min Act: -0.1700
Data Index: 4688507 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5360. Min Range: -5.5360
Max Act: 4.9735. Min Act: -0.1700
Data Index: 7006653 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5360. Min Range: -5.5360
Max Act: 5.0048. Min Act: -0.1700
Data Index: 3386317 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5360. Min Range: -5.5360
Max Act: 4.9735. Min Act: -0.1700
Data Index: 1407125 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5360. Min Range: -5.5360
Max Act: 5.0048. Min Act: -0.1700
Data Index: 4595125 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5360. Min Range: -5.5360
Max Act: 4.9735. Min Act: -0.1700
Data Index: 8137394 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5360. Min Range: -5.5360
Max Act: 5.0048. Min Act: -0.1700
Data Index: 6489811 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5360. Min Range: -5.5360
Max Act: 5.0048. Min Act: -0.1700
Data Index: 762995 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5360. Min Range: -5.5360
Max Act: 4.9423. Min Act: -0.1700
Data Index: 7973951 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5360. Min Range: -5.5360
Max Act: 4.8798. Min Act: -0.1700
Data Index: 789060 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5360. Min Range: -5.5360
Max Act: 4.9110. Min Act: -0.1700
Data Index: 3510362 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5360. Min Range: -5.5360
Max Act: 4.9110. Min Act: -0.1700
Data Index: 6090929 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5360. Min Range: -5.5360
Max Act: 4.9110. Min Act: -0.1700
Data Index: 4710641 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #19