Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3422 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1266. Min Range: -2.1266
Max Act: 2.1266. Min Act: -0.1700
Data Index: 2332162 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1266. Min Range: -2.1266
Max Act: 2.0764. Min Act: -0.1700
Data Index: 5552781 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1266. Min Range: -2.1266
Max Act: 2.0596. Min Act: -0.1700
Data Index: 6540385 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1266. Min Range: -2.1266
Max Act: 2.0428. Min Act: -0.1699
Data Index: 6848219 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1266. Min Range: -2.1266
Max Act: 2.0259. Min Act: -0.1697
Data Index: 1963819 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1266. Min Range: -2.1266
Max Act: 2.0428. Min Act: -0.1696
Data Index: 6393816 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1266. Min Range: -2.1266
Max Act: 2.0259. Min Act: -0.1700
Data Index: 2668426 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1266. Min Range: -2.1266
Max Act: 2.0175. Min Act: -0.1700
Data Index: 7557684 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1266. Min Range: -2.1266
Max Act: 2.0175. Min Act: -0.1695
Data Index: 6545559 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1266. Min Range: -2.1266
Max Act: 2.0259. Min Act: -0.1700
Data Index: 4062498 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1266. Min Range: -2.1266
Max Act: 2.0175. Min Act: -0.1635
Data Index: 2734918 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1266. Min Range: -2.1266
Max Act: 2.0259. Min Act: -0.1686
Data Index: 1076581 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1266. Min Range: -2.1266
Max Act: 2.0259. Min Act: -0.1699
Data Index: 7026828 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1266. Min Range: -2.1266
Max Act: 2.0175. Min Act: -0.1700
Data Index: 7282934 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1266. Min Range: -2.1266
Max Act: 2.0175. Min Act: -0.1697
Data Index: 5056985 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1266. Min Range: -2.1266
Max Act: 2.0175. Min Act: -0.1700
Data Index: 2591895 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1266. Min Range: -2.1266
Max Act: 2.0090. Min Act: -0.1695
Data Index: 220658 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1266. Min Range: -2.1266
Max Act: 2.0006. Min Act: -0.1674
Data Index: 5944180 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1266. Min Range: -2.1266
Max Act: 2.0090. Min Act: -0.1700
Data Index: 4047498 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1266. Min Range: -2.1266
Max Act: 2.0090. Min Act: -0.1685
Data Index: 7128924 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19