Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1018 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3903. Min Range: -6.3903
Max Act: 6.3903. Min Act: -0.1700
Data Index: 4402856 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3903. Min Range: -6.3903
Max Act: 6.1403. Min Act: -0.1700
Data Index: 3630058 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3903. Min Range: -6.3903
Max Act: 6.0466. Min Act: -0.1700
Data Index: 2284008 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3903. Min Range: -6.3903
Max Act: 6.0466. Min Act: -0.1700
Data Index: 3482204 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3903. Min Range: -6.3903
Max Act: 6.0153. Min Act: -0.1700
Data Index: 155008 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3903. Min Range: -6.3903
Max Act: 5.9528. Min Act: -0.1700
Data Index: 1916243 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3903. Min Range: -6.3903
Max Act: 5.9528. Min Act: -0.1700
Data Index: 6895596 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3903. Min Range: -6.3903
Max Act: 5.9528. Min Act: -0.1700
Data Index: 8715437 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3903. Min Range: -6.3903
Max Act: 5.9528. Min Act: -0.1700
Data Index: 3940025 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3903. Min Range: -6.3903
Max Act: 5.9216. Min Act: -0.1700
Data Index: 2795474 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3903. Min Range: -6.3903
Max Act: 5.9216. Min Act: -0.1700
Data Index: 3628189 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3903. Min Range: -6.3903
Max Act: 5.9216. Min Act: -0.1700
Data Index: 6289261 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3903. Min Range: -6.3903
Max Act: 5.8591. Min Act: -0.1700
Data Index: 1367386 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3903. Min Range: -6.3903
Max Act: 5.8903. Min Act: -0.1700
Data Index: 1764830 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3903. Min Range: -6.3903
Max Act: 5.8903. Min Act: -0.1700
Data Index: 7871685 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3903. Min Range: -6.3903
Max Act: 5.8591. Min Act: -0.1700
Data Index: 1662148 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3903. Min Range: -6.3903
Max Act: 5.8591. Min Act: -0.1700
Data Index: 1938648 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3903. Min Range: -6.3903
Max Act: 5.8278. Min Act: -0.1700
Data Index: 1349265 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3903. Min Range: -6.3903
Max Act: 5.8278. Min Act: -0.1700
Data Index: 1554583 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3903. Min Range: -6.3903
Max Act: 5.8591. Min Act: -0.1700
Data Index: 6156002 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19