Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1542 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6943. Min Range: -8.6943
Max Act: 8.6943. Min Act: -0.1700
Data Index: 2119371 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6943. Min Range: -8.6943
Max Act: 8.5068. Min Act: -0.1700
Data Index: 6588789 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6943. Min Range: -8.6943
Max Act: 8.5693. Min Act: -0.1700
Data Index: 6249709 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6943. Min Range: -8.6943
Max Act: 8.4443. Min Act: -0.1700
Data Index: 6569660 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6943. Min Range: -8.6943
Max Act: 8.3818. Min Act: -0.1700
Data Index: 1381211 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6943. Min Range: -8.6943
Max Act: 8.3193. Min Act: -0.1700
Data Index: 800787 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6943. Min Range: -8.6943
Max Act: 8.2568. Min Act: -0.1700
Data Index: 6970162 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6943. Min Range: -8.6943
Max Act: 8.2568. Min Act: -0.1700
Data Index: 1384568 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6943. Min Range: -8.6943
Max Act: 8.2568. Min Act: -0.1700
Data Index: 7153789 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6943. Min Range: -8.6943
Max Act: 8.2568. Min Act: -0.1700
Data Index: 1553387 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6943. Min Range: -8.6943
Max Act: 8.2568. Min Act: -0.1700
Data Index: 5699676 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6943. Min Range: -8.6943
Max Act: 8.1943. Min Act: -0.1700
Data Index: 3387034 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6943. Min Range: -8.6943
Max Act: 8.1943. Min Act: -0.1700
Data Index: 623303 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6943. Min Range: -8.6943
Max Act: 8.2568. Min Act: -0.1700
Data Index: 7104221 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6943. Min Range: -8.6943
Max Act: 8.1943. Min Act: -0.1700
Data Index: 3150472 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6943. Min Range: -8.6943
Max Act: 8.1318. Min Act: -0.1700
Data Index: 2318255 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6943. Min Range: -8.6943
Max Act: 8.1318. Min Act: -0.1700
Data Index: 7358078 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6943. Min Range: -8.6943
Max Act: 8.1318. Min Act: -0.1700
Data Index: 5721673 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6943. Min Range: -8.6943
Max Act: 8.0693. Min Act: -0.1700
Data Index: 6602213 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6943. Min Range: -8.6943
Max Act: 8.0693. Min Act: -0.1700
Data Index: 6682677 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19