Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4126 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.7366. Min Range: -1.7366
Max Act: 1.7366. Min Act: -0.1700
Data Index: 3510191 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7366. Min Range: -1.7366
Max Act: 1.7366. Min Act: -0.1700
Data Index: 5130321 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7366. Min Range: -1.7366
Max Act: 1.4221. Min Act: -0.1700
Data Index: 1786360 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7366. Min Range: -1.7366
Max Act: 1.4045. Min Act: -0.1700
Data Index: 6912945 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7366. Min Range: -1.7366
Max Act: 1.4045. Min Act: -0.1699
Data Index: 4899202 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7366. Min Range: -1.7366
Max Act: 1.3692. Min Act: -0.1700
Data Index: 5984272 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7366. Min Range: -1.7366
Max Act: 1.2810. Min Act: -0.1700
Data Index: 6008426 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7366. Min Range: -1.7366
Max Act: 1.2458. Min Act: -0.1700
Data Index: 554920 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7366. Min Range: -1.7366
Max Act: 1.2281. Min Act: -0.1700
Data Index: 7575879 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7366. Min Range: -1.7366
Max Act: 1.2281. Min Act: -0.1700
Data Index: 8191 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7366. Min Range: -1.7366
Max Act: 1.1401. Min Act: -0.1700
Data Index: 8068588 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7366. Min Range: -1.7366
Max Act: 1.1051. Min Act: -0.1700
Data Index: 1602624 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7366. Min Range: -1.7366
Max Act: 1.0526. Min Act: -0.1688
Data Index: 6337944 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7366. Min Range: -1.7366
Max Act: 1.0352. Min Act: -0.1692
Data Index: 5900526 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7366. Min Range: -1.7366
Max Act: 1.0352. Min Act: -0.1700
Data Index: 1771883 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7366. Min Range: -1.7366
Max Act: 1.0352. Min Act: -0.1687
Data Index: 2021840 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7366. Min Range: -1.7366
Max Act: 0.9830. Min Act: -0.1700
Data Index: 6608193 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7366. Min Range: -1.7366
Max Act: 0.9830. Min Act: -0.1700
Data Index: 1642438 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7366. Min Range: -1.7366
Max Act: 0.9657. Min Act: -0.1700
Data Index: 4521030 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7366. Min Range: -1.7366
Max Act: 0.9485. Min Act: -0.1699
Data Index: 6180262 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19