Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6346 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1310. Min Range: -6.1310
Max Act: 6.1310. Min Act: -0.1700
Data Index: 4443109 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1310. Min Range: -6.1310
Max Act: 6.0373. Min Act: -0.1700
Data Index: 5012932 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1310. Min Range: -6.1310
Max Act: 6.0060. Min Act: -0.1699
Data Index: 6492871 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1310. Min Range: -6.1310
Max Act: 6.0060. Min Act: -0.1700
Data Index: 7840825 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1310. Min Range: -6.1310
Max Act: 5.9748. Min Act: -0.1700
Data Index: 1289800 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1310. Min Range: -6.1310
Max Act: 5.9123. Min Act: -0.1700
Data Index: 8151625 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1310. Min Range: -6.1310
Max Act: 5.9123. Min Act: -0.1700
Data Index: 1214063 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1310. Min Range: -6.1310
Max Act: 5.8185. Min Act: -0.1700
Data Index: 964652 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1310. Min Range: -6.1310
Max Act: 5.7873. Min Act: -0.1700
Data Index: 867808 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1310. Min Range: -6.1310
Max Act: 5.7873. Min Act: -0.1700
Data Index: 8056663 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1310. Min Range: -6.1310
Max Act: 5.8185. Min Act: -0.1700
Data Index: 8192734 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1310. Min Range: -6.1310
Max Act: 5.8185. Min Act: -0.1700
Data Index: 5319932 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1310. Min Range: -6.1310
Max Act: 5.7873. Min Act: -0.1700
Data Index: 7992387 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1310. Min Range: -6.1310
Max Act: 5.7873. Min Act: -0.1700
Data Index: 1357632 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1310. Min Range: -6.1310
Max Act: 5.7873. Min Act: -0.1700
Data Index: 4470708 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1310. Min Range: -6.1310
Max Act: 5.7560. Min Act: -0.1700
Data Index: 1048433 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1310. Min Range: -6.1310
Max Act: 5.7560. Min Act: -0.1700
Data Index: 5278361 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1310. Min Range: -6.1310
Max Act: 5.7560. Min Act: -0.1700
Data Index: 4198393 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1310. Min Range: -6.1310
Max Act: 5.7248. Min Act: -0.1700
Data Index: 2343353 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1310. Min Range: -6.1310
Max Act: 5.7248. Min Act: -0.1700
Data Index: 5161702 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19