Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3763 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8633. Min Range: -9.8633
Max Act: 9.8633. Min Act: -0.1700
Data Index: 6230907 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8633. Min Range: -9.8633
Max Act: 9.8008. Min Act: -0.1700
Data Index: 7094136 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8633. Min Range: -9.8633
Max Act: 9.6758. Min Act: -0.1700
Data Index: 6116570 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8633. Min Range: -9.8633
Max Act: 9.6133. Min Act: -0.1700
Data Index: 8023580 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8633. Min Range: -9.8633
Max Act: 9.6133. Min Act: -0.1700
Data Index: 44592 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8633. Min Range: -9.8633
Max Act: 9.5508. Min Act: -0.1700
Data Index: 3720073 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8633. Min Range: -9.8633
Max Act: 9.6133. Min Act: -0.1700
Data Index: 5630422 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8633. Min Range: -9.8633
Max Act: 9.4883. Min Act: -0.1700
Data Index: 3457345 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8633. Min Range: -9.8633
Max Act: 9.4883. Min Act: -0.1700
Data Index: 5442129 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8633. Min Range: -9.8633
Max Act: 9.4883. Min Act: -0.1700
Data Index: 8198239 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8633. Min Range: -9.8633
Max Act: 9.4883. Min Act: -0.1700
Data Index: 5885754 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8633. Min Range: -9.8633
Max Act: 9.4258. Min Act: -0.1700
Data Index: 2624594 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8633. Min Range: -9.8633
Max Act: 9.4258. Min Act: -0.1700
Data Index: 484693 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8633. Min Range: -9.8633
Max Act: 9.3633. Min Act: -0.1700
Data Index: 3247836 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8633. Min Range: -9.8633
Max Act: 9.3633. Min Act: -0.1700
Data Index: 7923962 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8633. Min Range: -9.8633
Max Act: 9.3633. Min Act: -0.1700
Data Index: 847308 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8633. Min Range: -9.8633
Max Act: 9.3633. Min Act: -0.1700
Data Index: 330371 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8633. Min Range: -9.8633
Max Act: 9.3008. Min Act: -0.1700
Data Index: 7174618 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8633. Min Range: -9.8633
Max Act: 9.3008. Min Act: -0.1700
Data Index: 1424473 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8633. Min Range: -9.8633
Max Act: 9.3008. Min Act: -0.1700
Data Index: 273398 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #19