Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2564 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.6050. Min Act: -0.1700
Data Index: 2147096 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.6050. Min Act: -0.1700
Data Index: 1780561 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.6050. Min Act: -0.1700
Data Index: 7881104 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.5737. Min Act: -0.1700
Data Index: 4622574 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.5737. Min Act: -0.1700
Data Index: 3774160 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.5425. Min Act: -0.1700
Data Index: 1079537 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.5112. Min Act: -0.1700
Data Index: 8790524 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.4487. Min Act: -0.1700
Data Index: 3631661 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.4800. Min Act: -0.1700
Data Index: 2276637 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.4800. Min Act: -0.1700
Data Index: 4768300 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.5112. Min Act: -0.1700
Data Index: 6690417 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.4487. Min Act: -0.1700
Data Index: 251338 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.4487. Min Act: -0.1700
Data Index: 1968902 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.4175. Min Act: -0.1700
Data Index: 1780559 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.4175. Min Act: -0.1700
Data Index: 6046793 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.4175. Min Act: -0.1700
Data Index: 3039117 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.4175. Min Act: -0.1700
Data Index: 8046183 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.3862. Min Act: -0.1700
Data Index: 4055359 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.4175. Min Act: -0.1700
Data Index: 3758831 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.3862. Min Act: -0.1700
Data Index: 2713889 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19