Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4650 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1753. Min Range: -5.1753
Max Act: 5.1753. Min Act: -0.1700
Data Index: 3734449 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1753. Min Range: -5.1753
Max Act: 5.1440. Min Act: -0.1696
Data Index: 7803298 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1753. Min Range: -5.1753
Max Act: 5.1440. Min Act: -0.1697
Data Index: 6307192 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1753. Min Range: -5.1753
Max Act: 5.1440. Min Act: -0.1699
Data Index: 951092 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1753. Min Range: -5.1753
Max Act: 5.0815. Min Act: -0.1698
Data Index: 2844846 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1753. Min Range: -5.1753
Max Act: 5.1128. Min Act: -0.1699
Data Index: 6166919 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1753. Min Range: -5.1753
Max Act: 5.0503. Min Act: -0.1700
Data Index: 2993244 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1753. Min Range: -5.1753
Max Act: 5.0503. Min Act: -0.1700
Data Index: 7960988 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1753. Min Range: -5.1753
Max Act: 5.0503. Min Act: -0.1700
Data Index: 850288 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1753. Min Range: -5.1753
Max Act: 5.0190. Min Act: -0.1700
Data Index: 5460023 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1753. Min Range: -5.1753
Max Act: 5.0190. Min Act: -0.1700
Data Index: 2854251 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1753. Min Range: -5.1753
Max Act: 5.0190. Min Act: -0.1700
Data Index: 902128 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1753. Min Range: -5.1753
Max Act: 5.0190. Min Act: -0.1688
Data Index: 7980095 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1753. Min Range: -5.1753
Max Act: 5.0190. Min Act: -0.1700
Data Index: 212158 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1753. Min Range: -5.1753
Max Act: 4.9878. Min Act: -0.1700
Data Index: 5216682 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1753. Min Range: -5.1753
Max Act: 4.9878. Min Act: -0.1700
Data Index: 5192164 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1753. Min Range: -5.1753
Max Act: 4.9878. Min Act: -0.1700
Data Index: 1279225 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1753. Min Range: -5.1753
Max Act: 4.9878. Min Act: -0.1700
Data Index: 4896422 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1753. Min Range: -5.1753
Max Act: 4.9878. Min Act: -0.1697
Data Index: 7089182 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1753. Min Range: -5.1753
Max Act: 4.9878. Min Act: -0.1700
Data Index: 2864904 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19