Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3994 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2693. Min Range: -5.2693
Max Act: 5.2381. Min Act: -0.1700
Data Index: 6135599 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2693. Min Range: -5.2693
Max Act: 5.2693. Min Act: -0.1700
Data Index: 217903 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2693. Min Range: -5.2693
Max Act: 5.2381. Min Act: -0.1700
Data Index: 8652256 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2693. Min Range: -5.2693
Max Act: 5.2381. Min Act: -0.1700
Data Index: 54261 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2693. Min Range: -5.2693
Max Act: 5.2068. Min Act: -0.1700
Data Index: 4699887 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2693. Min Range: -5.2693
Max Act: 5.2068. Min Act: -0.1700
Data Index: 1864943 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2693. Min Range: -5.2693
Max Act: 5.1756. Min Act: -0.1700
Data Index: 7249505 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2693. Min Range: -5.2693
Max Act: 5.1756. Min Act: -0.1700
Data Index: 4497046 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2693. Min Range: -5.2693
Max Act: 5.1443. Min Act: -0.1700
Data Index: 8542793 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2693. Min Range: -5.2693
Max Act: 5.1756. Min Act: -0.1700
Data Index: 1339446 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2693. Min Range: -5.2693
Max Act: 5.1131. Min Act: -0.1700
Data Index: 5226697 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2693. Min Range: -5.2693
Max Act: 5.1443. Min Act: -0.1700
Data Index: 4174205 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2693. Min Range: -5.2693
Max Act: 5.0818. Min Act: -0.1700
Data Index: 2776019 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2693. Min Range: -5.2693
Max Act: 5.1131. Min Act: -0.1700
Data Index: 4662876 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2693. Min Range: -5.2693
Max Act: 5.1131. Min Act: -0.1700
Data Index: 2144414 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2693. Min Range: -5.2693
Max Act: 5.1131. Min Act: -0.1700
Data Index: 4658938 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2693. Min Range: -5.2693
Max Act: 5.1131. Min Act: -0.1700
Data Index: 5310089 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2693. Min Range: -5.2693
Max Act: 5.1131. Min Act: -0.1700
Data Index: 6970385 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2693. Min Range: -5.2693
Max Act: 5.0818. Min Act: -0.1700
Data Index: 1287338 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2693. Min Range: -5.2693
Max Act: 5.0818. Min Act: -0.1700
Data Index: 6653424 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19