Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3375 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0191. Min Range: -4.0191
Max Act: 4.0191. Min Act: -0.1700
Data Index: 5923747 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0191. Min Range: -4.0191
Max Act: 3.9566. Min Act: -0.1700
Data Index: 7054581 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0191. Min Range: -4.0191
Max Act: 3.8941. Min Act: -0.1700
Data Index: 8807393 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0191. Min Range: -4.0191
Max Act: 3.8628. Min Act: -0.1700
Data Index: 2024430 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0191. Min Range: -4.0191
Max Act: 3.7690. Min Act: -0.1700
Data Index: 4450348 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0191. Min Range: -4.0191
Max Act: 3.7690. Min Act: -0.1700
Data Index: 2513899 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0191. Min Range: -4.0191
Max Act: 3.7377. Min Act: -0.1700
Data Index: 7248079 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0191. Min Range: -4.0191
Max Act: 3.7377. Min Act: -0.1700
Data Index: 7999236 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0191. Min Range: -4.0191
Max Act: 3.7064. Min Act: -0.1700
Data Index: 8828196 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0191. Min Range: -4.0191
Max Act: 3.7064. Min Act: -0.1700
Data Index: 5107823 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0191. Min Range: -4.0191
Max Act: 3.7064. Min Act: -0.1700
Data Index: 2418018 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0191. Min Range: -4.0191
Max Act: 3.7064. Min Act: -0.1700
Data Index: 6411109 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0191. Min Range: -4.0191
Max Act: 3.6752. Min Act: -0.1700
Data Index: 1838365 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0191. Min Range: -4.0191
Max Act: 3.6752. Min Act: -0.1700
Data Index: 8807394 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0191. Min Range: -4.0191
Max Act: 3.6752. Min Act: -0.1700
Data Index: 3557775 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0191. Min Range: -4.0191
Max Act: 3.6752. Min Act: -0.1700
Data Index: 2554256 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0191. Min Range: -4.0191
Max Act: 3.6752. Min Act: -0.1700
Data Index: 8374518 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0191. Min Range: -4.0191
Max Act: 3.6752. Min Act: -0.1700
Data Index: 5152448 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0191. Min Range: -4.0191
Max Act: 3.6752. Min Act: -0.1700
Data Index: 3971408 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0191. Min Range: -4.0191
Max Act: 3.6439. Min Act: -0.1700
Data Index: 3538936 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19