Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2871 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3242. Min Range: -8.3242
Max Act: 8.3242. Min Act: -0.1700
Data Index: 6485525 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3242. Min Range: -8.3242
Max Act: 8.2617. Min Act: -0.1700
Data Index: 5896772 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3242. Min Range: -8.3242
Max Act: 8.0742. Min Act: -0.1700
Data Index: 1476263 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3242. Min Range: -8.3242
Max Act: 8.0117. Min Act: -0.1700
Data Index: 8265994 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3242. Min Range: -8.3242
Max Act: 7.9492. Min Act: -0.1700
Data Index: 3749877 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3242. Min Range: -8.3242
Max Act: 7.9492. Min Act: -0.1700
Data Index: 4276434 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3242. Min Range: -8.3242
Max Act: 8.0117. Min Act: -0.1700
Data Index: 2720163 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3242. Min Range: -8.3242
Max Act: 7.9492. Min Act: -0.1700
Data Index: 8626416 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3242. Min Range: -8.3242
Max Act: 7.8867. Min Act: -0.1700
Data Index: 1748780 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3242. Min Range: -8.3242
Max Act: 7.8242. Min Act: -0.1700
Data Index: 2235264 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3242. Min Range: -8.3242
Max Act: 7.8242. Min Act: -0.1700
Data Index: 6968231 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3242. Min Range: -8.3242
Max Act: 7.8242. Min Act: -0.1700
Data Index: 8340815 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3242. Min Range: -8.3242
Max Act: 7.7617. Min Act: -0.1700
Data Index: 359115 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3242. Min Range: -8.3242
Max Act: 7.7617. Min Act: -0.1700
Data Index: 5168902 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3242. Min Range: -8.3242
Max Act: 7.7617. Min Act: -0.1700
Data Index: 6432897 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3242. Min Range: -8.3242
Max Act: 7.7617. Min Act: -0.1700
Data Index: 269803 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3242. Min Range: -8.3242
Max Act: 7.6992. Min Act: -0.1700
Data Index: 3971805 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3242. Min Range: -8.3242
Max Act: 7.6992. Min Act: -0.1700
Data Index: 1214436 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3242. Min Range: -8.3242
Max Act: 7.7617. Min Act: -0.1700
Data Index: 2734298 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3242. Min Range: -8.3242
Max Act: 7.7617. Min Act: -0.1700
Data Index: 4228892 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #19