Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1965 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6513. Min Range: -1.6513
Max Act: 1.6513. Min Act: -0.1700
Data Index: 3616989 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6513. Min Range: -1.6513
Max Act: 1.6339. Min Act: -0.1700
Data Index: 7444740 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6513. Min Range: -1.6513
Max Act: 1.6252. Min Act: -0.1700
Data Index: 3265160 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6513. Min Range: -1.6513
Max Act: 1.6164. Min Act: -0.1700
Data Index: 5297601 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6513. Min Range: -1.6513
Max Act: 1.6077. Min Act: -0.1700
Data Index: 1129412 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6513. Min Range: -1.6513
Max Act: 1.5990. Min Act: -0.1700
Data Index: 1158204 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6513. Min Range: -1.6513
Max Act: 1.5902. Min Act: -0.1700
Data Index: 8152731 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6513. Min Range: -1.6513
Max Act: 1.5990. Min Act: -0.1700
Data Index: 3660481 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6513. Min Range: -1.6513
Max Act: 1.5990. Min Act: -0.1700
Data Index: 6633002 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6513. Min Range: -1.6513
Max Act: 1.5902. Min Act: -0.1700
Data Index: 3927341 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6513. Min Range: -1.6513
Max Act: 1.5902. Min Act: -0.1700
Data Index: 5085975 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6513. Min Range: -1.6513
Max Act: 1.5902. Min Act: -0.1700
Data Index: 4529005 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6513. Min Range: -1.6513
Max Act: 1.5902. Min Act: -0.1700
Data Index: 711876 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6513. Min Range: -1.6513
Max Act: 1.5815. Min Act: -0.1700
Data Index: 5292521 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6513. Min Range: -1.6513
Max Act: 1.5815. Min Act: -0.1700
Data Index: 3414446 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6513. Min Range: -1.6513
Max Act: 1.5815. Min Act: -0.1700
Data Index: 7140073 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6513. Min Range: -1.6513
Max Act: 1.5902. Min Act: -0.1700
Data Index: 6755529 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6513. Min Range: -1.6513
Max Act: 1.5728. Min Act: -0.1700
Data Index: 7857142 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6513. Min Range: -1.6513
Max Act: 1.5728. Min Act: -0.1700
Data Index: 2230098 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6513. Min Range: -1.6513
Max Act: 1.5728. Min Act: -0.1700
Data Index: 1892924 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19