Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3318 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0635. Min Range: -6.0635
Max Act: 6.0635. Min Act: -0.1700
Data Index: 1136172 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0635. Min Range: -6.0635
Max Act: 6.0635. Min Act: -0.1700
Data Index: 3651962 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0635. Min Range: -6.0635
Max Act: 6.0635. Min Act: -0.1700
Data Index: 6580631 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0635. Min Range: -6.0635
Max Act: 6.0323. Min Act: -0.1700
Data Index: 8084096 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0635. Min Range: -6.0635
Max Act: 6.0010. Min Act: -0.1700
Data Index: 8165202 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0635. Min Range: -6.0635
Max Act: 5.9698. Min Act: -0.1700
Data Index: 5958788 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0635. Min Range: -6.0635
Max Act: 6.0010. Min Act: -0.1700
Data Index: 6895302 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0635. Min Range: -6.0635
Max Act: 5.9698. Min Act: -0.1700
Data Index: 315468 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0635. Min Range: -6.0635
Max Act: 5.9698. Min Act: -0.1700
Data Index: 2575470 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0635. Min Range: -6.0635
Max Act: 5.9698. Min Act: -0.1700
Data Index: 6315045 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0635. Min Range: -6.0635
Max Act: 5.9698. Min Act: -0.1700
Data Index: 6805111 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0635. Min Range: -6.0635
Max Act: 5.9385. Min Act: -0.1700
Data Index: 6157627 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0635. Min Range: -6.0635
Max Act: 5.9385. Min Act: -0.1700
Data Index: 5252328 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0635. Min Range: -6.0635
Max Act: 5.9385. Min Act: -0.1700
Data Index: 6160549 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0635. Min Range: -6.0635
Max Act: 5.9073. Min Act: -0.1700
Data Index: 8255234 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0635. Min Range: -6.0635
Max Act: 5.9073. Min Act: -0.1700
Data Index: 1977369 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0635. Min Range: -6.0635
Max Act: 5.9073. Min Act: -0.1699
Data Index: 6384741 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0635. Min Range: -6.0635
Max Act: 5.9073. Min Act: -0.1700
Data Index: 4176161 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0635. Min Range: -6.0635
Max Act: 5.9073. Min Act: -0.1700
Data Index: 3735445 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0635. Min Range: -6.0635
Max Act: 5.8760. Min Act: -0.1700
Data Index: 6751439 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19