Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1248 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6944. Min Range: -5.6944
Max Act: 5.6944. Min Act: -0.1700
Data Index: 2515573 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6944. Min Range: -5.6944
Max Act: 5.6319. Min Act: -0.1700
Data Index: 8065889 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6944. Min Range: -5.6944
Max Act: 5.6319. Min Act: -0.1700
Data Index: 6473006 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6944. Min Range: -5.6944
Max Act: 5.5381. Min Act: -0.1700
Data Index: 7216397 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6944. Min Range: -5.6944
Max Act: 5.5381. Min Act: -0.1699
Data Index: 5367562 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6944. Min Range: -5.6944
Max Act: 5.4444. Min Act: -0.1700
Data Index: 4310600 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6944. Min Range: -5.6944
Max Act: 5.4756. Min Act: -0.1700
Data Index: 4185630 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6944. Min Range: -5.6944
Max Act: 5.4756. Min Act: -0.1700
Data Index: 2676920 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6944. Min Range: -5.6944
Max Act: 5.4444. Min Act: -0.1700
Data Index: 658022 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6944. Min Range: -5.6944
Max Act: 5.4444. Min Act: -0.1700
Data Index: 6068227 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6944. Min Range: -5.6944
Max Act: 5.4444. Min Act: -0.1700
Data Index: 3159207 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6944. Min Range: -5.6944
Max Act: 5.4444. Min Act: -0.1700
Data Index: 6443077 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6944. Min Range: -5.6944
Max Act: 5.4131. Min Act: -0.1700
Data Index: 2454862 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6944. Min Range: -5.6944
Max Act: 5.4131. Min Act: -0.1700
Data Index: 6675307 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6944. Min Range: -5.6944
Max Act: 5.4131. Min Act: -0.1700
Data Index: 3825936 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6944. Min Range: -5.6944
Max Act: 5.3506. Min Act: -0.1700
Data Index: 855155 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6944. Min Range: -5.6944
Max Act: 5.3819. Min Act: -0.1700
Data Index: 953897 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6944. Min Range: -5.6944
Max Act: 5.3819. Min Act: -0.1700
Data Index: 6536269 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6944. Min Range: -5.6944
Max Act: 5.3819. Min Act: -0.1700
Data Index: 7722742 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6944. Min Range: -5.6944
Max Act: 5.3506. Min Act: -0.1700
Data Index: 3554133 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19