Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1665 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.5187. Min Act: -0.1700
Data Index: 4437798 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.4874. Min Act: -0.1700
Data Index: 616746 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.4874. Min Act: -0.1700
Data Index: 8077230 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.4562. Min Act: -0.1700
Data Index: 2621230 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.3624. Min Act: -0.1700
Data Index: 3928139 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.2999. Min Act: -0.1700
Data Index: 6859427 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.3312. Min Act: -0.1700
Data Index: 5506648 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.2999. Min Act: -0.1700
Data Index: 6700738 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.2999. Min Act: -0.1700
Data Index: 8243382 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.2374. Min Act: -0.1700
Data Index: 7196215 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.2374. Min Act: -0.1700
Data Index: 260525 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.2374. Min Act: -0.1700
Data Index: 4506577 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.2062. Min Act: -0.1700
Data Index: 4605054 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.2062. Min Act: -0.1700
Data Index: 7165924 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.2062. Min Act: -0.1700
Data Index: 8641340 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.1749. Min Act: -0.1700
Data Index: 4045541 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.1749. Min Act: -0.1700
Data Index: 1049906 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.1749. Min Act: -0.1700
Data Index: 4122381 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.1749. Min Act: -0.1700
Data Index: 2222477 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.1437. Min Act: -0.1700
Data Index: 2104903 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19