Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3636 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1342. Min Range: -3.1342
Max Act: 3.1342. Min Act: -0.1700
Data Index: 4100124 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1342. Min Range: -3.1342
Max Act: 2.9447. Min Act: -0.1700
Data Index: 6232824 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1342. Min Range: -3.1342
Max Act: 2.8972. Min Act: -0.1700
Data Index: 4296952 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1342. Min Range: -3.1342
Max Act: 2.8813. Min Act: -0.1700
Data Index: 5197041 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1342. Min Range: -3.1342
Max Act: 2.8813. Min Act: -0.1700
Data Index: 8827117 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1342. Min Range: -3.1342
Max Act: 2.8654. Min Act: -0.1700
Data Index: 2928262 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1342. Min Range: -3.1342
Max Act: 2.8496. Min Act: -0.1700
Data Index: 3121486 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1342. Min Range: -3.1342
Max Act: 2.8337. Min Act: -0.1700
Data Index: 4553160 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1342. Min Range: -3.1342
Max Act: 2.8496. Min Act: -0.1700
Data Index: 6782 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1342. Min Range: -3.1342
Max Act: 2.8337. Min Act: -0.1700
Data Index: 8826880 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1342. Min Range: -3.1342
Max Act: 2.7859. Min Act: -0.1700
Data Index: 3320626 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1342. Min Range: -3.1342
Max Act: 2.8018. Min Act: -0.1700
Data Index: 4392197 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1342. Min Range: -3.1342
Max Act: 2.7859. Min Act: -0.1700
Data Index: 5882214 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1342. Min Range: -3.1342
Max Act: 2.7859. Min Act: -0.1700
Data Index: 6483787 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1342. Min Range: -3.1342
Max Act: 2.7859. Min Act: -0.1700
Data Index: 8820652 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1342. Min Range: -3.1342
Max Act: 2.7700. Min Act: -0.1700
Data Index: 5159521 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1342. Min Range: -3.1342
Max Act: 2.7540. Min Act: -0.1700
Data Index: 8392486 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1342. Min Range: -3.1342
Max Act: 2.7381. Min Act: -0.1700
Data Index: 1498982 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1342. Min Range: -3.1342
Max Act: 2.7381. Min Act: -0.1700
Data Index: 5717613 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1342. Min Range: -3.1342
Max Act: 2.7381. Min Act: -0.1700
Data Index: 6267589 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19