Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3919 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.1973. Min Range: -1.1973
Max Act: 1.1973. Min Act: -0.1700
Data Index: 2298173 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1973. Min Range: -1.1973
Max Act: 1.1094. Min Act: -0.1700
Data Index: 4362125 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1973. Min Range: -1.1973
Max Act: 1.0744. Min Act: -0.1700
Data Index: 8660136 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1973. Min Range: -1.1973
Max Act: 1.0570. Min Act: -0.1700
Data Index: 3547857 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1973. Min Range: -1.1973
Max Act: 1.0047. Min Act: -0.1699
Data Index: 164111 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1973. Min Range: -1.1973
Max Act: 0.9614. Min Act: -0.1700
Data Index: 7623332 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1973. Min Range: -1.1973
Max Act: 0.9701. Min Act: -0.1700
Data Index: 7704926 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1973. Min Range: -1.1973
Max Act: 0.9442. Min Act: -0.1700
Data Index: 1966675 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1973. Min Range: -1.1973
Max Act: 0.9442. Min Act: -0.1697
Data Index: 3637234 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1973. Min Range: -1.1973
Max Act: 0.9442. Min Act: -0.1700
Data Index: 3107529 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1973. Min Range: -1.1973
Max Act: 0.9184. Min Act: -0.1679
Data Index: 4845782 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1973. Min Range: -1.1973
Max Act: 0.9270. Min Act: -0.1700
Data Index: 4818369 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1973. Min Range: -1.1973
Max Act: 0.9270. Min Act: -0.1700
Data Index: 5379546 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1973. Min Range: -1.1973
Max Act: 0.9184. Min Act: -0.1700
Data Index: 907250 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1973. Min Range: -1.1973
Max Act: 0.9012. Min Act: -0.1700
Data Index: 7479332 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1973. Min Range: -1.1973
Max Act: 0.8927. Min Act: -0.1700
Data Index: 2775735 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1973. Min Range: -1.1973
Max Act: 0.8927. Min Act: -0.1700
Data Index: 6022995 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1973. Min Range: -1.1973
Max Act: 0.8842. Min Act: -0.1700
Data Index: 1774036 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1973. Min Range: -1.1973
Max Act: 0.8927. Min Act: -0.1693
Data Index: 6873216 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1973. Min Range: -1.1973
Max Act: 0.8756. Min Act: -0.1698
Data Index: 4455910 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19