Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2993 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.3360. Min Act: -0.1700
Data Index: 5440387 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.2889. Min Act: -0.1700
Data Index: 8706372 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.2575. Min Act: -0.1700
Data Index: 4467825 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.2104. Min Act: -0.1700
Data Index: 6339672 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.1946. Min Act: -0.1700
Data Index: 816829 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.2104. Min Act: -0.1700
Data Index: 133266 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.1317. Min Act: -0.1700
Data Index: 6207146 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.1317. Min Act: -0.1700
Data Index: 5185451 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.1317. Min Act: -0.1700
Data Index: 7000223 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.1159. Min Act: -0.1700
Data Index: 6549835 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.1159. Min Act: -0.1700
Data Index: 238078 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.1159. Min Act: -0.1700
Data Index: 902216 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.1159. Min Act: -0.1700
Data Index: 7342974 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.1002. Min Act: -0.1700
Data Index: 8247143 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.1002. Min Act: -0.1700
Data Index: 6866540 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.1002. Min Act: -0.1700
Data Index: 7230294 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.1002. Min Act: -0.1700
Data Index: 2595947 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.0844. Min Act: -0.1700
Data Index: 6282915 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.0844. Min Act: -0.1700
Data Index: 3021132 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.0844. Min Act: -0.1700
Data Index: 1592961 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #19