Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4460 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.8921. Min Act: -0.1700
Data Index: 5693611 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.8921. Min Act: -0.1700
Data Index: 7788324 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.8921. Min Act: -0.1700
Data Index: 8768581 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.8921. Min Act: -0.1700
Data Index: 7126069 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.8608. Min Act: -0.1700
Data Index: 1756043 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.8921. Min Act: -0.1700
Data Index: 6164842 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.8921. Min Act: -0.1700
Data Index: 8516809 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.8921. Min Act: -0.1700
Data Index: 2826849 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.8296. Min Act: -0.1700
Data Index: 6424218 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.7983. Min Act: -0.1700
Data Index: 5430031 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.7983. Min Act: -0.1700
Data Index: 2268007 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.7983. Min Act: -0.1700
Data Index: 6294706 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.7983. Min Act: -0.1700
Data Index: 4464155 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.7671. Min Act: -0.1700
Data Index: 2251735 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.7671. Min Act: -0.1700
Data Index: 8725792 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.7671. Min Act: -0.1700
Data Index: 6186760 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.7671. Min Act: -0.1700
Data Index: 1509722 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.7671. Min Act: -0.1700
Data Index: 784663 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.7671. Min Act: -0.1700
Data Index: 8145327 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.7358. Min Act: -0.1700
Data Index: 3235940 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19