Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3352 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.0146. Min Range: -11.0146
Max Act: 11.0146. Min Act: -0.1700
Data Index: 2130339 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0146. Min Range: -11.0146
Max Act: 10.5146. Min Act: -0.1700
Data Index: 5487211 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0146. Min Range: -11.0146
Max Act: 10.4521. Min Act: -0.1700
Data Index: 772551 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0146. Min Range: -11.0146
Max Act: 10.3896. Min Act: -0.1700
Data Index: 5238042 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0146. Min Range: -11.0146
Max Act: 10.3271. Min Act: -0.1700
Data Index: 6033241 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0146. Min Range: -11.0146
Max Act: 10.2646. Min Act: -0.1700
Data Index: 4132591 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0146. Min Range: -11.0146
Max Act: 10.2646. Min Act: -0.1700
Data Index: 4550624 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0146. Min Range: -11.0146
Max Act: 10.1396. Min Act: -0.1700
Data Index: 8791109 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0146. Min Range: -11.0146
Max Act: 10.1396. Min Act: -0.1700
Data Index: 4446098 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0146. Min Range: -11.0146
Max Act: 10.0771. Min Act: -0.1700
Data Index: 948448 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0146. Min Range: -11.0146
Max Act: 10.0771. Min Act: -0.1700
Data Index: 7210033 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0146. Min Range: -11.0146
Max Act: 10.0771. Min Act: -0.1700
Data Index: 3746329 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0146. Min Range: -11.0146
Max Act: 10.0771. Min Act: -0.1700
Data Index: 1192560 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0146. Min Range: -11.0146
Max Act: 10.0146. Min Act: -0.1700
Data Index: 8110601 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0146. Min Range: -11.0146
Max Act: 10.0146. Min Act: -0.1700
Data Index: 3260566 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0146. Min Range: -11.0146
Max Act: 9.9521. Min Act: -0.1700
Data Index: 8581600 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0146. Min Range: -11.0146
Max Act: 9.9521. Min Act: -0.1700
Data Index: 402911 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0146. Min Range: -11.0146
Max Act: 9.9521. Min Act: -0.1700
Data Index: 8634885 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0146. Min Range: -11.0146
Max Act: 9.8896. Min Act: -0.1700
Data Index: 1732023 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0146. Min Range: -11.0146
Max Act: 9.8271. Min Act: -0.1700
Data Index: 1492724 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #19