Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1649 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6186. Min Range: -6.6186
Max Act: 6.6186. Min Act: -0.1700
Data Index: 302270 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6186. Min Range: -6.6186
Max Act: 6.5874. Min Act: -0.1700
Data Index: 3439396 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6186. Min Range: -6.6186
Max Act: 6.5249. Min Act: -0.1700
Data Index: 7039763 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6186. Min Range: -6.6186
Max Act: 6.4311. Min Act: -0.1700
Data Index: 7807528 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6186. Min Range: -6.6186
Max Act: 6.4311. Min Act: -0.1700
Data Index: 5103315 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6186. Min Range: -6.6186
Max Act: 6.3686. Min Act: -0.1700
Data Index: 7567984 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6186. Min Range: -6.6186
Max Act: 6.3061. Min Act: -0.1700
Data Index: 3266609 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6186. Min Range: -6.6186
Max Act: 6.3374. Min Act: -0.1700
Data Index: 5162693 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6186. Min Range: -6.6186
Max Act: 6.3061. Min Act: -0.1700
Data Index: 5730410 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6186. Min Range: -6.6186
Max Act: 6.2749. Min Act: -0.1700
Data Index: 7378370 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6186. Min Range: -6.6186
Max Act: 6.2749. Min Act: -0.1700
Data Index: 358964 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6186. Min Range: -6.6186
Max Act: 6.2749. Min Act: -0.1700
Data Index: 3120816 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6186. Min Range: -6.6186
Max Act: 6.2749. Min Act: -0.1700
Data Index: 7971521 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6186. Min Range: -6.6186
Max Act: 6.2124. Min Act: -0.1700
Data Index: 1565398 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6186. Min Range: -6.6186
Max Act: 6.2124. Min Act: -0.1700
Data Index: 1220801 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6186. Min Range: -6.6186
Max Act: 6.2124. Min Act: -0.1700
Data Index: 7521967 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6186. Min Range: -6.6186
Max Act: 6.1811. Min Act: -0.1700
Data Index: 219964 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6186. Min Range: -6.6186
Max Act: 6.1811. Min Act: -0.1700
Data Index: 1146977 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6186. Min Range: -6.6186
Max Act: 6.1811. Min Act: -0.1700
Data Index: 7110333 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6186. Min Range: -6.6186
Max Act: 6.1499. Min Act: -0.1700
Data Index: 4281700 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19