Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1114 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7616. Min Range: -8.7616
Max Act: 8.7616. Min Act: -0.1700
Data Index: 5886941 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7616. Min Range: -8.7616
Max Act: 8.7616. Min Act: -0.1700
Data Index: 3454726 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7616. Min Range: -8.7616
Max Act: 8.6991. Min Act: -0.1700
Data Index: 1362732 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7616. Min Range: -8.7616
Max Act: 8.6991. Min Act: -0.1700
Data Index: 2183923 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7616. Min Range: -8.7616
Max Act: 8.6366. Min Act: -0.1700
Data Index: 6006524 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7616. Min Range: -8.7616
Max Act: 8.5741. Min Act: -0.1700
Data Index: 3898473 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7616. Min Range: -8.7616
Max Act: 8.5116. Min Act: -0.1700
Data Index: 741170 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7616. Min Range: -8.7616
Max Act: 8.4491. Min Act: -0.1700
Data Index: 6809054 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7616. Min Range: -8.7616
Max Act: 8.4491. Min Act: -0.1700
Data Index: 1708128 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7616. Min Range: -8.7616
Max Act: 8.4491. Min Act: -0.1700
Data Index: 7825346 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7616. Min Range: -8.7616
Max Act: 8.4491. Min Act: -0.1700
Data Index: 4119971 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7616. Min Range: -8.7616
Max Act: 8.3241. Min Act: -0.1700
Data Index: 3363830 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7616. Min Range: -8.7616
Max Act: 8.3866. Min Act: -0.1700
Data Index: 396351 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7616. Min Range: -8.7616
Max Act: 8.3866. Min Act: -0.1700
Data Index: 5231773 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7616. Min Range: -8.7616
Max Act: 8.3866. Min Act: -0.1700
Data Index: 7923731 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7616. Min Range: -8.7616
Max Act: 8.3866. Min Act: -0.1700
Data Index: 7111449 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7616. Min Range: -8.7616
Max Act: 8.3241. Min Act: -0.1700
Data Index: 2374340 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7616. Min Range: -8.7616
Max Act: 8.3241. Min Act: -0.1700
Data Index: 5455422 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7616. Min Range: -8.7616
Max Act: 8.3241. Min Act: -0.1700
Data Index: 6340529 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7616. Min Range: -8.7616
Max Act: 8.3241. Min Act: -0.1700
Data Index: 6760224 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19