Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3804 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8608. Min Range: -5.8608
Max Act: 5.8608. Min Act: -0.1700
Data Index: 3936802 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8608. Min Range: -5.8608
Max Act: 5.7358. Min Act: -0.1700
Data Index: 5073928 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8608. Min Range: -5.8608
Max Act: 5.6733. Min Act: -0.1700
Data Index: 7283700 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8608. Min Range: -5.8608
Max Act: 5.6421. Min Act: -0.1700
Data Index: 8239455 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8608. Min Range: -5.8608
Max Act: 5.5796. Min Act: -0.1700
Data Index: 127168 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8608. Min Range: -5.8608
Max Act: 5.5796. Min Act: -0.1700
Data Index: 3642529 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8608. Min Range: -5.8608
Max Act: 5.5796. Min Act: -0.1700
Data Index: 6921879 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8608. Min Range: -5.8608
Max Act: 5.5483. Min Act: -0.1700
Data Index: 1013684 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8608. Min Range: -5.8608
Max Act: 5.5171. Min Act: -0.1700
Data Index: 5382289 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8608. Min Range: -5.8608
Max Act: 5.4858. Min Act: -0.1700
Data Index: 2928198 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8608. Min Range: -5.8608
Max Act: 5.4546. Min Act: -0.1700
Data Index: 5410278 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8608. Min Range: -5.8608
Max Act: 5.4233. Min Act: -0.1700
Data Index: 7461837 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8608. Min Range: -5.8608
Max Act: 5.4546. Min Act: -0.1700
Data Index: 4898950 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8608. Min Range: -5.8608
Max Act: 5.4546. Min Act: -0.1700
Data Index: 5015348 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8608. Min Range: -5.8608
Max Act: 5.4233. Min Act: -0.1700
Data Index: 3658047 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8608. Min Range: -5.8608
Max Act: 5.4546. Min Act: -0.1700
Data Index: 8295591 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8608. Min Range: -5.8608
Max Act: 5.4546. Min Act: -0.1700
Data Index: 5084554 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8608. Min Range: -5.8608
Max Act: 5.4546. Min Act: -0.1700
Data Index: 6185391 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8608. Min Range: -5.8608
Max Act: 5.4233. Min Act: -0.1700
Data Index: 3733043 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8608. Min Range: -5.8608
Max Act: 5.3921. Min Act: -0.1700
Data Index: 3786242 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #19