Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1555 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2521. Min Range: -8.2521
Max Act: 8.2521. Min Act: -0.1700
Data Index: 1011563 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2521. Min Range: -8.2521
Max Act: 7.7521. Min Act: -0.1700
Data Index: 8790440 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2521. Min Range: -8.2521
Max Act: 7.6896. Min Act: -0.1700
Data Index: 5652427 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2521. Min Range: -8.2521
Max Act: 7.6271. Min Act: -0.1700
Data Index: 3560664 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2521. Min Range: -8.2521
Max Act: 7.5646. Min Act: -0.1700
Data Index: 6924898 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2521. Min Range: -8.2521
Max Act: 7.4396. Min Act: -0.1700
Data Index: 1880184 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2521. Min Range: -8.2521
Max Act: 7.4083. Min Act: -0.1700
Data Index: 6201096 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2521. Min Range: -8.2521
Max Act: 7.3146. Min Act: -0.1700
Data Index: 2263086 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2521. Min Range: -8.2521
Max Act: 7.3146. Min Act: -0.1700
Data Index: 1708601 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2521. Min Range: -8.2521
Max Act: 7.2521. Min Act: -0.1700
Data Index: 4190545 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2521. Min Range: -8.2521
Max Act: 7.2833. Min Act: -0.1700
Data Index: 6051757 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2521. Min Range: -8.2521
Max Act: 7.2521. Min Act: -0.1700
Data Index: 1431197 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2521. Min Range: -8.2521
Max Act: 7.2521. Min Act: -0.1700
Data Index: 8714372 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2521. Min Range: -8.2521
Max Act: 7.2521. Min Act: -0.1700
Data Index: 8034518 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2521. Min Range: -8.2521
Max Act: 7.2208. Min Act: -0.1700
Data Index: 3300995 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2521. Min Range: -8.2521
Max Act: 7.2208. Min Act: -0.1700
Data Index: 1219576 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2521. Min Range: -8.2521
Max Act: 7.2208. Min Act: -0.1700
Data Index: 7786860 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2521. Min Range: -8.2521
Max Act: 7.2521. Min Act: -0.1700
Data Index: 7342418 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2521. Min Range: -8.2521
Max Act: 7.2208. Min Act: -0.1700
Data Index: 44017 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2521. Min Range: -8.2521
Max Act: 7.2208. Min Act: -0.1700
Data Index: 4774665 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19