Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2357 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3769. Min Range: -4.3769
Max Act: 4.3769. Min Act: -0.1700
Data Index: 4487585 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3769. Min Range: -4.3769
Max Act: 4.2519. Min Act: -0.1700
Data Index: 5151518 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3769. Min Range: -4.3769
Max Act: 4.2207. Min Act: -0.1700
Data Index: 2642849 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3769. Min Range: -4.3769
Max Act: 4.1269. Min Act: -0.1700
Data Index: 5410788 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3769. Min Range: -4.3769
Max Act: 4.1269. Min Act: -0.1700
Data Index: 8609369 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3769. Min Range: -4.3769
Max Act: 4.1269. Min Act: -0.1700
Data Index: 467632 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3769. Min Range: -4.3769
Max Act: 4.0956. Min Act: -0.1700
Data Index: 1071325 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3769. Min Range: -4.3769
Max Act: 4.0956. Min Act: -0.1700
Data Index: 2475866 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3769. Min Range: -4.3769
Max Act: 4.1269. Min Act: -0.1700
Data Index: 7713163 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3769. Min Range: -4.3769
Max Act: 4.0956. Min Act: -0.1700
Data Index: 5349853 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3769. Min Range: -4.3769
Max Act: 4.0956. Min Act: -0.1700
Data Index: 5798818 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3769. Min Range: -4.3769
Max Act: 4.0956. Min Act: -0.1700
Data Index: 952671 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3769. Min Range: -4.3769
Max Act: 4.0644. Min Act: -0.1700
Data Index: 7039621 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3769. Min Range: -4.3769
Max Act: 4.0644. Min Act: -0.1700
Data Index: 2508084 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3769. Min Range: -4.3769
Max Act: 3.9706. Min Act: -0.1700
Data Index: 3766059 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3769. Min Range: -4.3769
Max Act: 4.0019. Min Act: -0.1700
Data Index: 3516863 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3769. Min Range: -4.3769
Max Act: 4.0019. Min Act: -0.1700
Data Index: 1660908 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3769. Min Range: -4.3769
Max Act: 4.0331. Min Act: -0.1700
Data Index: 3208395 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3769. Min Range: -4.3769
Max Act: 4.0331. Min Act: -0.1700
Data Index: 4936772 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3769. Min Range: -4.3769
Max Act: 4.0019. Min Act: -0.1700
Data Index: 7892855 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19