Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1066 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8133. Min Range: -7.8133
Max Act: 7.8133. Min Act: -0.1700
Data Index: 2003241 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8133. Min Range: -7.8133
Max Act: 7.7195. Min Act: -0.1700
Data Index: 8642410 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8133. Min Range: -7.8133
Max Act: 7.5633. Min Act: -0.1700
Data Index: 4324074 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8133. Min Range: -7.8133
Max Act: 7.5320. Min Act: -0.1700
Data Index: 2731884 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8133. Min Range: -7.8133
Max Act: 7.3758. Min Act: -0.1700
Data Index: 8084755 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8133. Min Range: -7.8133
Max Act: 7.3133. Min Act: -0.1700
Data Index: 5376399 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8133. Min Range: -7.8133
Max Act: 7.3133. Min Act: -0.1700
Data Index: 3260222 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8133. Min Range: -7.8133
Max Act: 7.3133. Min Act: -0.1700
Data Index: 425274 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8133. Min Range: -7.8133
Max Act: 7.2820. Min Act: -0.1700
Data Index: 5137604 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8133. Min Range: -7.8133
Max Act: 7.1258. Min Act: -0.1700
Data Index: 1029353 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8133. Min Range: -7.8133
Max Act: 7.0945. Min Act: -0.1700
Data Index: 2072638 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8133. Min Range: -7.8133
Max Act: 7.0945. Min Act: -0.1700
Data Index: 5254037 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8133. Min Range: -7.8133
Max Act: 7.0945. Min Act: -0.1700
Data Index: 6066442 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8133. Min Range: -7.8133
Max Act: 7.0320. Min Act: -0.1700
Data Index: 860114 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8133. Min Range: -7.8133
Max Act: 7.0008. Min Act: -0.1700
Data Index: 5119293 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8133. Min Range: -7.8133
Max Act: 7.0320. Min Act: -0.1700
Data Index: 4514839 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8133. Min Range: -7.8133
Max Act: 7.0008. Min Act: -0.1700
Data Index: 5847410 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8133. Min Range: -7.8133
Max Act: 7.0008. Min Act: -0.1700
Data Index: 8575052 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8133. Min Range: -7.8133
Max Act: 7.0008. Min Act: -0.1700
Data Index: 5598352 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8133. Min Range: -7.8133
Max Act: 7.0008. Min Act: -0.1700
Data Index: 4533016 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19