Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3274 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8075. Min Range: -4.8075
Max Act: 4.8075. Min Act: -0.1700
Data Index: 2870746 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8075. Min Range: -4.8075
Max Act: 4.7450. Min Act: -0.1700
Data Index: 868258 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8075. Min Range: -4.8075
Max Act: 4.7137. Min Act: -0.1700
Data Index: 335873 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8075. Min Range: -4.8075
Max Act: 4.6825. Min Act: -0.1700
Data Index: 5887986 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8075. Min Range: -4.8075
Max Act: 4.6512. Min Act: -0.1700
Data Index: 7826005 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8075. Min Range: -4.8075
Max Act: 4.6200. Min Act: -0.1700
Data Index: 1106078 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8075. Min Range: -4.8075
Max Act: 4.6200. Min Act: -0.1700
Data Index: 5210060 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8075. Min Range: -4.8075
Max Act: 4.5887. Min Act: -0.1700
Data Index: 7788742 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8075. Min Range: -4.8075
Max Act: 4.5887. Min Act: -0.1700
Data Index: 2306846 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8075. Min Range: -4.8075
Max Act: 4.5575. Min Act: -0.1700
Data Index: 6431328 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8075. Min Range: -4.8075
Max Act: 4.5575. Min Act: -0.1700
Data Index: 4938532 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8075. Min Range: -4.8075
Max Act: 4.5575. Min Act: -0.1700
Data Index: 7184223 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8075. Min Range: -4.8075
Max Act: 4.5575. Min Act: -0.1700
Data Index: 3223472 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8075. Min Range: -4.8075
Max Act: 4.5262. Min Act: -0.1700
Data Index: 46377 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8075. Min Range: -4.8075
Max Act: 4.5262. Min Act: -0.1700
Data Index: 5439397 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8075. Min Range: -4.8075
Max Act: 4.4950. Min Act: -0.1700
Data Index: 23516 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8075. Min Range: -4.8075
Max Act: 4.4950. Min Act: -0.1700
Data Index: 4024164 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8075. Min Range: -4.8075
Max Act: 4.4950. Min Act: -0.1700
Data Index: 1707308 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8075. Min Range: -4.8075
Max Act: 4.4950. Min Act: -0.1700
Data Index: 1106584 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8075. Min Range: -4.8075
Max Act: 4.4637. Min Act: -0.1700
Data Index: 1146166 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19