Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2900 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7654. Min Range: -4.7654
Max Act: 4.7654. Min Act: -0.1700
Data Index: 2511524 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7654. Min Range: -4.7654
Max Act: 4.6717. Min Act: -0.1700
Data Index: 5530969 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7654. Min Range: -4.7654
Max Act: 4.6092. Min Act: -0.1700
Data Index: 3056049 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7654. Min Range: -4.7654
Max Act: 4.6092. Min Act: -0.1700
Data Index: 4440543 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7654. Min Range: -4.7654
Max Act: 4.5779. Min Act: -0.1700
Data Index: 3109154 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7654. Min Range: -4.7654
Max Act: 4.6092. Min Act: -0.1700
Data Index: 1397698 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7654. Min Range: -4.7654
Max Act: 4.5779. Min Act: -0.1700
Data Index: 4437240 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7654. Min Range: -4.7654
Max Act: 4.5467. Min Act: -0.1700
Data Index: 3790022 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7654. Min Range: -4.7654
Max Act: 4.5779. Min Act: -0.1700
Data Index: 4333929 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7654. Min Range: -4.7654
Max Act: 4.5154. Min Act: -0.1700
Data Index: 895669 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7654. Min Range: -4.7654
Max Act: 4.5154. Min Act: -0.1700
Data Index: 6334046 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7654. Min Range: -4.7654
Max Act: 4.5154. Min Act: -0.1700
Data Index: 4643676 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7654. Min Range: -4.7654
Max Act: 4.5154. Min Act: -0.1700
Data Index: 1910029 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7654. Min Range: -4.7654
Max Act: 4.5154. Min Act: -0.1700
Data Index: 7621042 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7654. Min Range: -4.7654
Max Act: 4.4842. Min Act: -0.1700
Data Index: 3808833 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7654. Min Range: -4.7654
Max Act: 4.4842. Min Act: -0.1700
Data Index: 415583 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7654. Min Range: -4.7654
Max Act: 4.4529. Min Act: -0.1700
Data Index: 5652545 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7654. Min Range: -4.7654
Max Act: 4.4529. Min Act: -0.1700
Data Index: 1530803 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7654. Min Range: -4.7654
Max Act: 4.4529. Min Act: -0.1700
Data Index: 7052 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7654. Min Range: -4.7654
Max Act: 4.4529. Min Act: -0.1700
Data Index: 4887642 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19