Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3406 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1307. Min Range: -9.1307
Max Act: 9.1307. Min Act: -0.1700
Data Index: 267704 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1307. Min Range: -9.1307
Max Act: 8.6932. Min Act: -0.1700
Data Index: 2383261 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1307. Min Range: -9.1307
Max Act: 8.6932. Min Act: -0.1700
Data Index: 4882422 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1307. Min Range: -9.1307
Max Act: 8.6307. Min Act: -0.1700
Data Index: 925105 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1307. Min Range: -9.1307
Max Act: 8.5057. Min Act: -0.1700
Data Index: 3940493 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1307. Min Range: -9.1307
Max Act: 8.4432. Min Act: -0.1700
Data Index: 3641190 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1307. Min Range: -9.1307
Max Act: 8.4432. Min Act: -0.1700
Data Index: 2468131 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1307. Min Range: -9.1307
Max Act: 8.4432. Min Act: -0.1700
Data Index: 5255834 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1307. Min Range: -9.1307
Max Act: 8.3807. Min Act: -0.1700
Data Index: 6513112 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1307. Min Range: -9.1307
Max Act: 8.3807. Min Act: -0.1700
Data Index: 8556544 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1307. Min Range: -9.1307
Max Act: 8.3182. Min Act: -0.1700
Data Index: 8268358 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1307. Min Range: -9.1307
Max Act: 8.3182. Min Act: -0.1700
Data Index: 193696 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1307. Min Range: -9.1307
Max Act: 8.2557. Min Act: -0.1700
Data Index: 686321 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1307. Min Range: -9.1307
Max Act: 8.2557. Min Act: -0.1700
Data Index: 236361 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1307. Min Range: -9.1307
Max Act: 8.1932. Min Act: -0.1700
Data Index: 5079939 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1307. Min Range: -9.1307
Max Act: 8.1932. Min Act: -0.1700
Data Index: 1044755 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1307. Min Range: -9.1307
Max Act: 8.1932. Min Act: -0.1700
Data Index: 6872967 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1307. Min Range: -9.1307
Max Act: 8.1307. Min Act: -0.1700
Data Index: 49669 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1307. Min Range: -9.1307
Max Act: 8.0682. Min Act: -0.1700
Data Index: 4179118 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1307. Min Range: -9.1307
Max Act: 8.1307. Min Act: -0.1700
Data Index: 6019408 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19