Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2928 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3297. Min Range: -9.3297
Max Act: 9.3297. Min Act: -0.1700
Data Index: 364262 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3297. Min Range: -9.3297
Max Act: 9.2047. Min Act: -0.1700
Data Index: 3334249 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3297. Min Range: -9.3297
Max Act: 9.2047. Min Act: -0.1700
Data Index: 2305260 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3297. Min Range: -9.3297
Max Act: 9.0172. Min Act: -0.1700
Data Index: 3321265 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3297. Min Range: -9.3297
Max Act: 8.8922. Min Act: -0.1700
Data Index: 964926 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3297. Min Range: -9.3297
Max Act: 8.8922. Min Act: -0.1700
Data Index: 711589 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3297. Min Range: -9.3297
Max Act: 8.8922. Min Act: -0.1700
Data Index: 4083931 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3297. Min Range: -9.3297
Max Act: 8.8297. Min Act: -0.1700
Data Index: 87687 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3297. Min Range: -9.3297
Max Act: 8.8297. Min Act: -0.1700
Data Index: 3997536 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3297. Min Range: -9.3297
Max Act: 8.8297. Min Act: -0.1700
Data Index: 5641098 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3297. Min Range: -9.3297
Max Act: 8.8297. Min Act: -0.1700
Data Index: 5947895 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3297. Min Range: -9.3297
Max Act: 8.8297. Min Act: -0.1700
Data Index: 5862659 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3297. Min Range: -9.3297
Max Act: 8.8297. Min Act: -0.1700
Data Index: 3198617 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3297. Min Range: -9.3297
Max Act: 8.8297. Min Act: -0.1700
Data Index: 5750797 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3297. Min Range: -9.3297
Max Act: 8.7672. Min Act: -0.1700
Data Index: 4240743 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3297. Min Range: -9.3297
Max Act: 8.7672. Min Act: -0.1700
Data Index: 138857 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3297. Min Range: -9.3297
Max Act: 8.7672. Min Act: -0.1700
Data Index: 6943558 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3297. Min Range: -9.3297
Max Act: 8.7672. Min Act: -0.1700
Data Index: 739621 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3297. Min Range: -9.3297
Max Act: 8.6422. Min Act: -0.1700
Data Index: 1973315 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3297. Min Range: -9.3297
Max Act: 8.7047. Min Act: -0.1700
Data Index: 4828288 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19