Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1816 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9619. Min Range: -4.9619
Max Act: 4.9619. Min Act: -0.1700
Data Index: 7843719 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9619. Min Range: -4.9619
Max Act: 4.8994. Min Act: -0.1700
Data Index: 3184370 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9619. Min Range: -4.9619
Max Act: 4.8369. Min Act: -0.1700
Data Index: 379635 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9619. Min Range: -4.9619
Max Act: 4.8056. Min Act: -0.1700
Data Index: 2852239 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9619. Min Range: -4.9619
Max Act: 4.7744. Min Act: -0.1700
Data Index: 7533904 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9619. Min Range: -4.9619
Max Act: 4.7744. Min Act: -0.1700
Data Index: 4588854 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9619. Min Range: -4.9619
Max Act: 4.7431. Min Act: -0.1700
Data Index: 3983003 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9619. Min Range: -4.9619
Max Act: 4.7431. Min Act: -0.1700
Data Index: 1297309 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9619. Min Range: -4.9619
Max Act: 4.7431. Min Act: -0.1700
Data Index: 3292515 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9619. Min Range: -4.9619
Max Act: 4.7431. Min Act: -0.1700
Data Index: 3083027 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9619. Min Range: -4.9619
Max Act: 4.7431. Min Act: -0.1700
Data Index: 6812021 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9619. Min Range: -4.9619
Max Act: 4.7431. Min Act: -0.1700
Data Index: 1494366 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9619. Min Range: -4.9619
Max Act: 4.7119. Min Act: -0.1700
Data Index: 3846026 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9619. Min Range: -4.9619
Max Act: 4.7119. Min Act: -0.1700
Data Index: 7893054 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9619. Min Range: -4.9619
Max Act: 4.7119. Min Act: -0.1700
Data Index: 8674673 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9619. Min Range: -4.9619
Max Act: 4.7119. Min Act: -0.1700
Data Index: 7829056 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9619. Min Range: -4.9619
Max Act: 4.7119. Min Act: -0.1700
Data Index: 6446429 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9619. Min Range: -4.9619
Max Act: 4.6806. Min Act: -0.1700
Data Index: 4443659 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9619. Min Range: -4.9619
Max Act: 4.7119. Min Act: -0.1700
Data Index: 3600608 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9619. Min Range: -4.9619
Max Act: 4.6806. Min Act: -0.1700
Data Index: 8010155 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19