Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3800 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1480. Min Range: -4.1480
Max Act: 4.1480. Min Act: -0.1700
Data Index: 7008818 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1480. Min Range: -4.1480
Max Act: 4.1167. Min Act: -0.1700
Data Index: 3097603 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1480. Min Range: -4.1480
Max Act: 3.9291. Min Act: -0.1700
Data Index: 884301 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1480. Min Range: -4.1480
Max Act: 3.9291. Min Act: -0.1700
Data Index: 8438496 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1480. Min Range: -4.1480
Max Act: 3.8979. Min Act: -0.1700
Data Index: 4135209 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1480. Min Range: -4.1480
Max Act: 3.9291. Min Act: -0.1700
Data Index: 7350679 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1480. Min Range: -4.1480
Max Act: 3.9291. Min Act: -0.1700
Data Index: 150494 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1480. Min Range: -4.1480
Max Act: 3.8979. Min Act: -0.1700
Data Index: 1059084 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1480. Min Range: -4.1480
Max Act: 3.8666. Min Act: -0.1700
Data Index: 3087926 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1480. Min Range: -4.1480
Max Act: 3.8666. Min Act: -0.1700
Data Index: 7201111 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1480. Min Range: -4.1480
Max Act: 3.8666. Min Act: -0.1700
Data Index: 5896847 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1480. Min Range: -4.1480
Max Act: 3.8666. Min Act: -0.1700
Data Index: 460288 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1480. Min Range: -4.1480
Max Act: 3.8666. Min Act: -0.1700
Data Index: 5060605 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1480. Min Range: -4.1480
Max Act: 3.8041. Min Act: -0.1700
Data Index: 1059080 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1480. Min Range: -4.1480
Max Act: 3.8353. Min Act: -0.1700
Data Index: 3467074 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1480. Min Range: -4.1480
Max Act: 3.8353. Min Act: -0.1700
Data Index: 6897543 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1480. Min Range: -4.1480
Max Act: 3.8041. Min Act: -0.1700
Data Index: 7876988 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1480. Min Range: -4.1480
Max Act: 3.8353. Min Act: -0.1700
Data Index: 4496372 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1480. Min Range: -4.1480
Max Act: 3.8041. Min Act: -0.1700
Data Index: 8005771 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1480. Min Range: -4.1480
Max Act: 3.8353. Min Act: -0.1700
Data Index: 5135689 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19