Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2831 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0506. Min Range: -6.0506
Max Act: 6.0506. Min Act: -0.1700
Data Index: 8468012 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0506. Min Range: -6.0506
Max Act: 5.7694. Min Act: -0.1700
Data Index: 6415138 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0506. Min Range: -6.0506
Max Act: 5.7381. Min Act: -0.1700
Data Index: 7250900 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0506. Min Range: -6.0506
Max Act: 5.6756. Min Act: -0.1700
Data Index: 6483557 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0506. Min Range: -6.0506
Max Act: 5.6444. Min Act: -0.1700
Data Index: 7003117 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0506. Min Range: -6.0506
Max Act: 5.6444. Min Act: -0.1700
Data Index: 6620619 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0506. Min Range: -6.0506
Max Act: 5.6131. Min Act: -0.1700
Data Index: 7250919 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0506. Min Range: -6.0506
Max Act: 5.5506. Min Act: -0.1700
Data Index: 3594576 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0506. Min Range: -6.0506
Max Act: 5.5194. Min Act: -0.1700
Data Index: 7509607 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0506. Min Range: -6.0506
Max Act: 5.4881. Min Act: -0.1700
Data Index: 6273815 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0506. Min Range: -6.0506
Max Act: 5.4881. Min Act: -0.1700
Data Index: 3569104 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0506. Min Range: -6.0506
Max Act: 5.4881. Min Act: -0.1700
Data Index: 296543 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0506. Min Range: -6.0506
Max Act: 5.4256. Min Act: -0.1700
Data Index: 7250901 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0506. Min Range: -6.0506
Max Act: 5.4256. Min Act: -0.1700
Data Index: 5328441 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0506. Min Range: -6.0506
Max Act: 5.4256. Min Act: -0.1700
Data Index: 5171227 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0506. Min Range: -6.0506
Max Act: 5.4256. Min Act: -0.1700
Data Index: 7212919 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0506. Min Range: -6.0506
Max Act: 5.3944. Min Act: -0.1700
Data Index: 5575965 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0506. Min Range: -6.0506
Max Act: 5.3944. Min Act: -0.1700
Data Index: 203943 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0506. Min Range: -6.0506
Max Act: 5.3944. Min Act: -0.1700
Data Index: 3182595 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0506. Min Range: -6.0506
Max Act: 5.3944. Min Act: -0.1700
Data Index: 2918376 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19