Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2786 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4956. Min Range: -8.4956
Max Act: 8.4956. Min Act: -0.1700
Data Index: 8029507 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4956. Min Range: -8.4956
Max Act: 8.3081. Min Act: -0.1700
Data Index: 6097244 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4956. Min Range: -8.4956
Max Act: 8.1206. Min Act: -0.1700
Data Index: 6915866 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4956. Min Range: -8.4956
Max Act: 7.9956. Min Act: -0.1700
Data Index: 4657653 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4956. Min Range: -8.4956
Max Act: 8.1206. Min Act: -0.1700
Data Index: 3414217 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4956. Min Range: -8.4956
Max Act: 7.9956. Min Act: -0.1700
Data Index: 1456315 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4956. Min Range: -8.4956
Max Act: 8.0581. Min Act: -0.1700
Data Index: 6421169 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4956. Min Range: -8.4956
Max Act: 7.9956. Min Act: -0.1700
Data Index: 3103335 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4956. Min Range: -8.4956
Max Act: 7.9331. Min Act: -0.1700
Data Index: 6902143 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4956. Min Range: -8.4956
Max Act: 7.9331. Min Act: -0.1700
Data Index: 3497086 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4956. Min Range: -8.4956
Max Act: 7.9331. Min Act: -0.1700
Data Index: 4482083 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4956. Min Range: -8.4956
Max Act: 7.9331. Min Act: -0.1700
Data Index: 7902441 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4956. Min Range: -8.4956
Max Act: 7.9019. Min Act: -0.1700
Data Index: 3691104 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4956. Min Range: -8.4956
Max Act: 7.8706. Min Act: -0.1700
Data Index: 8106267 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4956. Min Range: -8.4956
Max Act: 7.8394. Min Act: -0.1700
Data Index: 2803026 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4956. Min Range: -8.4956
Max Act: 7.8394. Min Act: -0.1700
Data Index: 4609950 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4956. Min Range: -8.4956
Max Act: 7.8394. Min Act: -0.1700
Data Index: 477668 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4956. Min Range: -8.4956
Max Act: 7.8394. Min Act: -0.1700
Data Index: 2971851 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4956. Min Range: -8.4956
Max Act: 7.8081. Min Act: -0.1700
Data Index: 5989460 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4956. Min Range: -8.4956
Max Act: 7.7769. Min Act: -0.1700
Data Index: 233344 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19