Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4905 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4804. Min Range: -4.4804
Max Act: 4.4804. Min Act: -0.1700
Data Index: 4924355 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4804. Min Range: -4.4804
Max Act: 4.4804. Min Act: -0.1700
Data Index: 1955560 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4804. Min Range: -4.4804
Max Act: 4.4179. Min Act: -0.1700
Data Index: 1827184 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4804. Min Range: -4.4804
Max Act: 4.4179. Min Act: -0.1700
Data Index: 5715247 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4804. Min Range: -4.4804
Max Act: 4.3554. Min Act: -0.1700
Data Index: 5987696 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4804. Min Range: -4.4804
Max Act: 4.3241. Min Act: -0.1700
Data Index: 7069128 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4804. Min Range: -4.4804
Max Act: 4.2929. Min Act: -0.1700
Data Index: 1008631 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4804. Min Range: -4.4804
Max Act: 4.2304. Min Act: -0.1700
Data Index: 3287376 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4804. Min Range: -4.4804
Max Act: 4.2616. Min Act: -0.1700
Data Index: 6022149 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4804. Min Range: -4.4804
Max Act: 4.1991. Min Act: -0.1700
Data Index: 1106538 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4804. Min Range: -4.4804
Max Act: 4.1991. Min Act: -0.1700
Data Index: 5733625 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4804. Min Range: -4.4804
Max Act: 4.1991. Min Act: -0.1700
Data Index: 6171035 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4804. Min Range: -4.4804
Max Act: 4.1991. Min Act: -0.1700
Data Index: 433465 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4804. Min Range: -4.4804
Max Act: 4.1991. Min Act: -0.1700
Data Index: 3750987 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4804. Min Range: -4.4804
Max Act: 4.1679. Min Act: -0.1700
Data Index: 5544185 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4804. Min Range: -4.4804
Max Act: 4.1679. Min Act: -0.1700
Data Index: 1948886 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4804. Min Range: -4.4804
Max Act: 4.1679. Min Act: -0.1700
Data Index: 4476654 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4804. Min Range: -4.4804
Max Act: 4.1366. Min Act: -0.1700
Data Index: 7053231 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4804. Min Range: -4.4804
Max Act: 4.1366. Min Act: -0.1700
Data Index: 442712 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4804. Min Range: -4.4804
Max Act: 4.1366. Min Act: -0.1700
Data Index: 6593328 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19