Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 578 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8348. Min Range: -5.8348
Max Act: 5.8348. Min Act: -0.1700
Data Index: 7071736 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8348. Min Range: -5.8348
Max Act: 5.7723. Min Act: -0.1700
Data Index: 1564352 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8348. Min Range: -5.8348
Max Act: 5.7723. Min Act: -0.1700
Data Index: 117258 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8348. Min Range: -5.8348
Max Act: 5.7723. Min Act: -0.1700
Data Index: 2138016 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8348. Min Range: -5.8348
Max Act: 5.7098. Min Act: -0.1700
Data Index: 1364627 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8348. Min Range: -5.8348
Max Act: 5.7098. Min Act: -0.1700
Data Index: 7806925 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8348. Min Range: -5.8348
Max Act: 5.7098. Min Act: -0.1700
Data Index: 7193214 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8348. Min Range: -5.8348
Max Act: 5.6473. Min Act: -0.1700
Data Index: 3877051 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8348. Min Range: -5.8348
Max Act: 5.6786. Min Act: -0.1700
Data Index: 5328671 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8348. Min Range: -5.8348
Max Act: 5.6786. Min Act: -0.1700
Data Index: 7922327 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8348. Min Range: -5.8348
Max Act: 5.6473. Min Act: -0.1700
Data Index: 458128 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8348. Min Range: -5.8348
Max Act: 5.6473. Min Act: -0.1700
Data Index: 1540513 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8348. Min Range: -5.8348
Max Act: 5.6473. Min Act: -0.1700
Data Index: 4284392 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8348. Min Range: -5.8348
Max Act: 5.6161. Min Act: -0.1700
Data Index: 1256223 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8348. Min Range: -5.8348
Max Act: 5.5848. Min Act: -0.1700
Data Index: 2673242 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8348. Min Range: -5.8348
Max Act: 5.6161. Min Act: -0.1700
Data Index: 8496122 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8348. Min Range: -5.8348
Max Act: 5.5848. Min Act: -0.1700
Data Index: 7323029 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8348. Min Range: -5.8348
Max Act: 5.5536. Min Act: -0.1700
Data Index: 7661267 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8348. Min Range: -5.8348
Max Act: 5.5848. Min Act: -0.1700
Data Index: 4753196 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8348. Min Range: -5.8348
Max Act: 5.5848. Min Act: -0.1700
Data Index: 7193215 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19