Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4181 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5557. Min Range: -5.5557
Max Act: 5.5557. Min Act: -0.1700
Data Index: 7154180 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5557. Min Range: -5.5557
Max Act: 5.4932. Min Act: -0.1700
Data Index: 6877471 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5557. Min Range: -5.5557
Max Act: 5.3057. Min Act: -0.1700
Data Index: 5281029 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5557. Min Range: -5.5557
Max Act: 5.3057. Min Act: -0.1700
Data Index: 498563 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5557. Min Range: -5.5557
Max Act: 5.2432. Min Act: -0.1700
Data Index: 5813813 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5557. Min Range: -5.5557
Max Act: 5.2432. Min Act: -0.1700
Data Index: 4244633 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5557. Min Range: -5.5557
Max Act: 5.2432. Min Act: -0.1700
Data Index: 5862856 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5557. Min Range: -5.5557
Max Act: 5.2119. Min Act: -0.1700
Data Index: 5849392 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5557. Min Range: -5.5557
Max Act: 5.1807. Min Act: -0.1700
Data Index: 1332828 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5557. Min Range: -5.5557
Max Act: 5.2119. Min Act: -0.1700
Data Index: 211998 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5557. Min Range: -5.5557
Max Act: 5.2119. Min Act: -0.1700
Data Index: 4351451 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5557. Min Range: -5.5557
Max Act: 5.1807. Min Act: -0.1700
Data Index: 6070298 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5557. Min Range: -5.5557
Max Act: 5.1494. Min Act: -0.1700
Data Index: 6746647 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5557. Min Range: -5.5557
Max Act: 5.1807. Min Act: -0.1700
Data Index: 5332142 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5557. Min Range: -5.5557
Max Act: 5.1807. Min Act: -0.1700
Data Index: 1094218 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5557. Min Range: -5.5557
Max Act: 5.1494. Min Act: -0.1700
Data Index: 6554595 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5557. Min Range: -5.5557
Max Act: 5.1494. Min Act: -0.1700
Data Index: 2570357 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5557. Min Range: -5.5557
Max Act: 5.1182. Min Act: -0.1700
Data Index: 6571632 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5557. Min Range: -5.5557
Max Act: 5.1182. Min Act: -0.1700
Data Index: 5231568 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5557. Min Range: -5.5557
Max Act: 5.1182. Min Act: -0.1700
Data Index: 774362 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19