Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4947 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0967. Min Range: -5.0967
Max Act: 5.0967. Min Act: -0.1700
Data Index: 2388755 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0967. Min Range: -5.0967
Max Act: 5.0967. Min Act: -0.1700
Data Index: 2114719 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0967. Min Range: -5.0967
Max Act: 5.0030. Min Act: -0.1700
Data Index: 269121 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0967. Min Range: -5.0967
Max Act: 4.9717. Min Act: -0.1700
Data Index: 3593219 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0967. Min Range: -5.0967
Max Act: 4.9405. Min Act: -0.1700
Data Index: 3879312 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0967. Min Range: -5.0967
Max Act: 4.9405. Min Act: -0.1700
Data Index: 2613675 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0967. Min Range: -5.0967
Max Act: 4.9405. Min Act: -0.1700
Data Index: 464684 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0967. Min Range: -5.0967
Max Act: 4.9405. Min Act: -0.1700
Data Index: 4918857 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0967. Min Range: -5.0967
Max Act: 4.9092. Min Act: -0.1700
Data Index: 5879957 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0967. Min Range: -5.0967
Max Act: 4.8780. Min Act: -0.1700
Data Index: 3587461 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0967. Min Range: -5.0967
Max Act: 4.9092. Min Act: -0.1700
Data Index: 6654572 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0967. Min Range: -5.0967
Max Act: 4.8780. Min Act: -0.1700
Data Index: 5661818 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0967. Min Range: -5.0967
Max Act: 4.8780. Min Act: -0.1700
Data Index: 5394088 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0967. Min Range: -5.0967
Max Act: 4.8467. Min Act: -0.1700
Data Index: 6144753 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0967. Min Range: -5.0967
Max Act: 4.8155. Min Act: -0.1700
Data Index: 5143672 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0967. Min Range: -5.0967
Max Act: 4.8155. Min Act: -0.1700
Data Index: 8747969 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0967. Min Range: -5.0967
Max Act: 4.8155. Min Act: -0.1700
Data Index: 2444708 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0967. Min Range: -5.0967
Max Act: 4.8155. Min Act: -0.1700
Data Index: 5306381 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0967. Min Range: -5.0967
Max Act: 4.7530. Min Act: -0.1700
Data Index: 3193079 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0967. Min Range: -5.0967
Max Act: 4.7530. Min Act: -0.1700
Data Index: 5683909 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19