Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1815 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4777. Min Range: -3.4777
Max Act: 3.4777. Min Act: -0.1700
Data Index: 7926618 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4777. Min Range: -3.4777
Max Act: 3.4464. Min Act: -0.1700
Data Index: 8294517 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4777. Min Range: -3.4777
Max Act: 3.4150. Min Act: -0.1700
Data Index: 8443178 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4777. Min Range: -3.4777
Max Act: 3.3523. Min Act: -0.1700
Data Index: 4165750 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4777. Min Range: -3.4777
Max Act: 3.3680. Min Act: -0.1700
Data Index: 2469232 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4777. Min Range: -3.4777
Max Act: 3.3366. Min Act: -0.1700
Data Index: 4085790 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4777. Min Range: -3.4777
Max Act: 3.3209. Min Act: -0.1700
Data Index: 6570069 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4777. Min Range: -3.4777
Max Act: 3.3052. Min Act: -0.1700
Data Index: 7487366 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4777. Min Range: -3.4777
Max Act: 3.2738. Min Act: -0.1700
Data Index: 8789853 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4777. Min Range: -3.4777
Max Act: 3.2738. Min Act: -0.1700
Data Index: 6997285 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4777. Min Range: -3.4777
Max Act: 3.2581. Min Act: -0.1700
Data Index: 4132135 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4777. Min Range: -3.4777
Max Act: 3.2424. Min Act: -0.1700
Data Index: 8714875 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4777. Min Range: -3.4777
Max Act: 3.2424. Min Act: -0.1700
Data Index: 7767690 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4777. Min Range: -3.4777
Max Act: 3.2424. Min Act: -0.1700
Data Index: 7085028 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4777. Min Range: -3.4777
Max Act: 3.2110. Min Act: -0.1700
Data Index: 704335 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4777. Min Range: -3.4777
Max Act: 3.2424. Min Act: -0.1700
Data Index: 1941749 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4777. Min Range: -3.4777
Max Act: 3.2267. Min Act: -0.1700
Data Index: 7437830 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4777. Min Range: -3.4777
Max Act: 3.2267. Min Act: -0.1700
Data Index: 7127370 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4777. Min Range: -3.4777
Max Act: 3.1795. Min Act: -0.1700
Data Index: 969053 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4777. Min Range: -3.4777
Max Act: 3.1952. Min Act: -0.1700
Data Index: 6982077 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19