Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5140 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0150. Min Range: -4.0150
Max Act: 4.0150. Min Act: -0.1700
Data Index: 6077089 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0150. Min Range: -4.0150
Max Act: 3.8900. Min Act: -0.1700
Data Index: 699486 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0150. Min Range: -4.0150
Max Act: 3.8743. Min Act: -0.1700
Data Index: 217028 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0150. Min Range: -4.0150
Max Act: 3.7805. Min Act: -0.1700
Data Index: 2624211 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0150. Min Range: -4.0150
Max Act: 3.7649. Min Act: -0.1700
Data Index: 955584 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0150. Min Range: -4.0150
Max Act: 3.7023. Min Act: -0.1700
Data Index: 3991038 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0150. Min Range: -4.0150
Max Act: 3.7180. Min Act: -0.1700
Data Index: 6961192 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0150. Min Range: -4.0150
Max Act: 3.7023. Min Act: -0.1700
Data Index: 4002550 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0150. Min Range: -4.0150
Max Act: 3.6867. Min Act: -0.1700
Data Index: 5555563 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0150. Min Range: -4.0150
Max Act: 3.6710. Min Act: -0.1700
Data Index: 1958376 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0150. Min Range: -4.0150
Max Act: 3.6241. Min Act: -0.1700
Data Index: 200192 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0150. Min Range: -4.0150
Max Act: 3.5928. Min Act: -0.1700
Data Index: 2293855 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0150. Min Range: -4.0150
Max Act: 3.5771. Min Act: -0.1700
Data Index: 1291674 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0150. Min Range: -4.0150
Max Act: 3.5928. Min Act: -0.1700
Data Index: 3140224 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0150. Min Range: -4.0150
Max Act: 3.5615. Min Act: -0.1700
Data Index: 8649926 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0150. Min Range: -4.0150
Max Act: 3.5458. Min Act: -0.1700
Data Index: 4882176 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0150. Min Range: -4.0150
Max Act: 3.5145. Min Act: -0.1700
Data Index: 8322948 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0150. Min Range: -4.0150
Max Act: 3.5145. Min Act: -0.1700
Data Index: 8041195 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0150. Min Range: -4.0150
Max Act: 3.4988. Min Act: -0.1700
Data Index: 6162780 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0150. Min Range: -4.0150
Max Act: 3.4988. Min Act: -0.1700
Data Index: 2631813 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19