Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2946 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.4916. Min Range: -9.4916
Max Act: 9.4916. Min Act: -0.1700
Data Index: 5970060 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4916. Min Range: -9.4916
Max Act: 9.2416. Min Act: -0.1700
Data Index: 8131798 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4916. Min Range: -9.4916
Max Act: 9.3041. Min Act: -0.1700
Data Index: 7184027 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4916. Min Range: -9.4916
Max Act: 9.2416. Min Act: -0.1700
Data Index: 4515680 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4916. Min Range: -9.4916
Max Act: 9.1791. Min Act: -0.1700
Data Index: 5665668 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4916. Min Range: -9.4916
Max Act: 9.1791. Min Act: -0.1700
Data Index: 1025912 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4916. Min Range: -9.4916
Max Act: 9.1166. Min Act: -0.1700
Data Index: 5547563 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4916. Min Range: -9.4916
Max Act: 9.1166. Min Act: -0.1700
Data Index: 123116 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4916. Min Range: -9.4916
Max Act: 9.0541. Min Act: -0.1700
Data Index: 3702704 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4916. Min Range: -9.4916
Max Act: 9.0541. Min Act: -0.1700
Data Index: 1521710 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4916. Min Range: -9.4916
Max Act: 8.9916. Min Act: -0.1700
Data Index: 3624371 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4916. Min Range: -9.4916
Max Act: 8.9916. Min Act: -0.1700
Data Index: 1352777 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4916. Min Range: -9.4916
Max Act: 8.9916. Min Act: -0.1700
Data Index: 5384702 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4916. Min Range: -9.4916
Max Act: 8.9291. Min Act: -0.1700
Data Index: 8445283 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4916. Min Range: -9.4916
Max Act: 8.9291. Min Act: -0.1700
Data Index: 8052168 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4916. Min Range: -9.4916
Max Act: 8.8666. Min Act: -0.1700
Data Index: 6475465 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4916. Min Range: -9.4916
Max Act: 8.8666. Min Act: -0.1700
Data Index: 2797182 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4916. Min Range: -9.4916
Max Act: 8.8666. Min Act: -0.1700
Data Index: 5752568 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4916. Min Range: -9.4916
Max Act: 8.8666. Min Act: -0.1700
Data Index: 8235485 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4916. Min Range: -9.4916
Max Act: 8.8666. Min Act: -0.1700
Data Index: 4497231 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19