Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4518 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3721. Min Range: -3.3721
Max Act: 3.3721. Min Act: -0.1700
Data Index: 6013652 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3721. Min Range: -3.3721
Max Act: 3.3094. Min Act: -0.1700
Data Index: 5655077 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3721. Min Range: -3.3721
Max Act: 3.3094. Min Act: -0.1700
Data Index: 6013650 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3721. Min Range: -3.3721
Max Act: 3.2151. Min Act: -0.1700
Data Index: 2077413 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3721. Min Range: -3.3721
Max Act: 3.1837. Min Act: -0.1700
Data Index: 5854964 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3721. Min Range: -3.3721
Max Act: 3.1679. Min Act: -0.1700
Data Index: 2336179 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3721. Min Range: -3.3721
Max Act: 3.1365. Min Act: -0.1700
Data Index: 6013654 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3721. Min Range: -3.3721
Max Act: 3.1365. Min Act: -0.1700
Data Index: 8456082 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3721. Min Range: -3.3721
Max Act: 3.1365. Min Act: -0.1700
Data Index: 1812911 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3721. Min Range: -3.3721
Max Act: 3.1207. Min Act: -0.1700
Data Index: 5933881 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3721. Min Range: -3.3721
Max Act: 3.1207. Min Act: -0.1700
Data Index: 2002791 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3721. Min Range: -3.3721
Max Act: 3.1207. Min Act: -0.1700
Data Index: 810212 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3721. Min Range: -3.3721
Max Act: 3.1050. Min Act: -0.1700
Data Index: 4854203 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3721. Min Range: -3.3721
Max Act: 3.0892. Min Act: -0.1700
Data Index: 8095898 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3721. Min Range: -3.3721
Max Act: 3.1050. Min Act: -0.1700
Data Index: 6006906 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3721. Min Range: -3.3721
Max Act: 3.0734. Min Act: -0.1700
Data Index: 4966974 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3721. Min Range: -3.3721
Max Act: 3.0734. Min Act: -0.1700
Data Index: 531372 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3721. Min Range: -3.3721
Max Act: 3.0577. Min Act: -0.1700
Data Index: 7709630 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3721. Min Range: -3.3721
Max Act: 3.0577. Min Act: -0.1700
Data Index: 6416234 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3721. Min Range: -3.3721
Max Act: 3.0577. Min Act: -0.1700
Data Index: 4243472 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19