Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2678 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9258. Min Range: -5.9258
Max Act: 5.9258. Min Act: -0.1700
Data Index: 2218199 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9258. Min Range: -5.9258
Max Act: 5.7071. Min Act: -0.1700
Data Index: 3300587 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9258. Min Range: -5.9258
Max Act: 5.7071. Min Act: -0.1700
Data Index: 8458493 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9258. Min Range: -5.9258
Max Act: 5.6758. Min Act: -0.1700
Data Index: 7142907 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9258. Min Range: -5.9258
Max Act: 5.6446. Min Act: -0.1700
Data Index: 1661121 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9258. Min Range: -5.9258
Max Act: 5.6133. Min Act: -0.1700
Data Index: 8105394 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9258. Min Range: -5.9258
Max Act: 5.6133. Min Act: -0.1700
Data Index: 4369426 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9258. Min Range: -5.9258
Max Act: 5.5821. Min Act: -0.1700
Data Index: 4609396 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9258. Min Range: -5.9258
Max Act: 5.5821. Min Act: -0.1700
Data Index: 3758519 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9258. Min Range: -5.9258
Max Act: 5.5508. Min Act: -0.1700
Data Index: 4802810 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9258. Min Range: -5.9258
Max Act: 5.5508. Min Act: -0.1700
Data Index: 6619209 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9258. Min Range: -5.9258
Max Act: 5.5196. Min Act: -0.1700
Data Index: 2984390 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9258. Min Range: -5.9258
Max Act: 5.4883. Min Act: -0.1700
Data Index: 4296946 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9258. Min Range: -5.9258
Max Act: 5.4883. Min Act: -0.1700
Data Index: 1610427 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9258. Min Range: -5.9258
Max Act: 5.4883. Min Act: -0.1700
Data Index: 6843533 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9258. Min Range: -5.9258
Max Act: 5.4571. Min Act: -0.1700
Data Index: 1189466 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9258. Min Range: -5.9258
Max Act: 5.4258. Min Act: -0.1700
Data Index: 2976714 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9258. Min Range: -5.9258
Max Act: 5.4258. Min Act: -0.1700
Data Index: 7498150 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9258. Min Range: -5.9258
Max Act: 5.4258. Min Act: -0.1700
Data Index: 7739809 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9258. Min Range: -5.9258
Max Act: 5.3946. Min Act: -0.1700
Data Index: 5819043 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19