Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3455 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5276. Min Range: -6.5276
Max Act: 6.5276. Min Act: -0.1700
Data Index: 4547014 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5276. Min Range: -6.5276
Max Act: 6.4964. Min Act: -0.1700
Data Index: 8263387 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5276. Min Range: -6.5276
Max Act: 6.4026. Min Act: -0.1700
Data Index: 645253 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5276. Min Range: -6.5276
Max Act: 6.3401. Min Act: -0.1700
Data Index: 2843845 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5276. Min Range: -6.5276
Max Act: 6.3401. Min Act: -0.1700
Data Index: 3739612 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5276. Min Range: -6.5276
Max Act: 6.3089. Min Act: -0.1700
Data Index: 1696375 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5276. Min Range: -6.5276
Max Act: 6.2776. Min Act: -0.1700
Data Index: 6518799 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5276. Min Range: -6.5276
Max Act: 6.2151. Min Act: -0.1700
Data Index: 4317209 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5276. Min Range: -6.5276
Max Act: 6.1839. Min Act: -0.1700
Data Index: 1727041 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5276. Min Range: -6.5276
Max Act: 6.1839. Min Act: -0.1700
Data Index: 5823312 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5276. Min Range: -6.5276
Max Act: 6.1214. Min Act: -0.1700
Data Index: 5356172 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5276. Min Range: -6.5276
Max Act: 6.1214. Min Act: -0.1700
Data Index: 5139957 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5276. Min Range: -6.5276
Max Act: 6.0276. Min Act: -0.1700
Data Index: 2973252 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5276. Min Range: -6.5276
Max Act: 6.0276. Min Act: -0.1700
Data Index: 285199 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5276. Min Range: -6.5276
Max Act: 6.0276. Min Act: -0.1700
Data Index: 7070676 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5276. Min Range: -6.5276
Max Act: 6.0276. Min Act: -0.1700
Data Index: 1085052 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5276. Min Range: -6.5276
Max Act: 5.9964. Min Act: -0.1700
Data Index: 3786905 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5276. Min Range: -6.5276
Max Act: 5.9964. Min Act: -0.1700
Data Index: 1008553 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5276. Min Range: -6.5276
Max Act: 5.9964. Min Act: -0.1700
Data Index: 2999722 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5276. Min Range: -6.5276
Max Act: 5.9964. Min Act: -0.1700
Data Index: 6767611 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19