Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2900 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1740. Min Range: -8.1740
Max Act: 8.1740. Min Act: -0.1700
Data Index: 304113 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1740. Min Range: -8.1740
Max Act: 8.1115. Min Act: -0.1700
Data Index: 4928623 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1740. Min Range: -8.1740
Max Act: 8.0490. Min Act: -0.1700
Data Index: 8703455 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1740. Min Range: -8.1740
Max Act: 7.8615. Min Act: -0.1700
Data Index: 4639052 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1740. Min Range: -8.1740
Max Act: 7.9240. Min Act: -0.1700
Data Index: 4295656 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1740. Min Range: -8.1740
Max Act: 7.8615. Min Act: -0.1700
Data Index: 977514 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1740. Min Range: -8.1740
Max Act: 7.7990. Min Act: -0.1700
Data Index: 1378780 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1740. Min Range: -8.1740
Max Act: 7.7365. Min Act: -0.1700
Data Index: 6652097 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1740. Min Range: -8.1740
Max Act: 7.6740. Min Act: -0.1700
Data Index: 8386704 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1740. Min Range: -8.1740
Max Act: 7.6740. Min Act: -0.1700
Data Index: 2527939 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1740. Min Range: -8.1740
Max Act: 7.6740. Min Act: -0.1700
Data Index: 7153889 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1740. Min Range: -8.1740
Max Act: 7.6740. Min Act: -0.1700
Data Index: 5055507 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1740. Min Range: -8.1740
Max Act: 7.6740. Min Act: -0.1700
Data Index: 1473860 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1740. Min Range: -8.1740
Max Act: 7.6740. Min Act: -0.1700
Data Index: 3561348 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1740. Min Range: -8.1740
Max Act: 7.6115. Min Act: -0.1700
Data Index: 767983 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1740. Min Range: -8.1740
Max Act: 7.5802. Min Act: -0.1700
Data Index: 5383886 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1740. Min Range: -8.1740
Max Act: 7.5490. Min Act: -0.1700
Data Index: 6315482 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1740. Min Range: -8.1740
Max Act: 7.5802. Min Act: -0.1700
Data Index: 2678807 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1740. Min Range: -8.1740
Max Act: 7.5490. Min Act: -0.1700
Data Index: 534391 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1740. Min Range: -8.1740
Max Act: 7.5802. Min Act: -0.1700
Data Index: 7103955 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19