Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1068 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.2867. Min Act: -0.1700
Data Index: 1175161 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.2867. Min Act: -0.1700
Data Index: 5551748 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.2554. Min Act: -0.1700
Data Index: 5326566 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.2242. Min Act: -0.1700
Data Index: 1474988 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.2242. Min Act: -0.1700
Data Index: 3719328 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.1929. Min Act: -0.1700
Data Index: 2572192 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.1304. Min Act: -0.1700
Data Index: 6410615 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.1617. Min Act: -0.1700
Data Index: 8523131 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.1304. Min Act: -0.1700
Data Index: 6761887 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.1304. Min Act: -0.1700
Data Index: 3042345 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.1304. Min Act: -0.1700
Data Index: 8414342 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0992. Min Act: -0.1700
Data Index: 7760305 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0992. Min Act: -0.1700
Data Index: 8488276 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0992. Min Act: -0.1700
Data Index: 4064532 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0679. Min Act: -0.1700
Data Index: 4095625 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0679. Min Act: -0.1700
Data Index: 4333299 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0679. Min Act: -0.1700
Data Index: 3194746 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0054. Min Act: -0.1700
Data Index: 7859082 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0367. Min Act: -0.1700
Data Index: 7247172 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0367. Min Act: -0.1700
Data Index: 6723363 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19