Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 464 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4261. Min Range: -6.4261
Max Act: 6.4261. Min Act: -0.1700
Data Index: 8327062 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4261. Min Range: -6.4261
Max Act: 6.3948. Min Act: -0.1700
Data Index: 2186952 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4261. Min Range: -6.4261
Max Act: 6.2386. Min Act: -0.1700
Data Index: 156749 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4261. Min Range: -6.4261
Max Act: 6.2073. Min Act: -0.1700
Data Index: 2186951 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4261. Min Range: -6.4261
Max Act: 6.2073. Min Act: -0.1700
Data Index: 6869690 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4261. Min Range: -6.4261
Max Act: 6.1761. Min Act: -0.1700
Data Index: 5273800 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4261. Min Range: -6.4261
Max Act: 6.1761. Min Act: -0.1700
Data Index: 1033449 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4261. Min Range: -6.4261
Max Act: 6.1761. Min Act: -0.1700
Data Index: 1771951 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4261. Min Range: -6.4261
Max Act: 6.1448. Min Act: -0.1700
Data Index: 5456934 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4261. Min Range: -6.4261
Max Act: 6.1136. Min Act: -0.1700
Data Index: 5823530 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4261. Min Range: -6.4261
Max Act: 6.1136. Min Act: -0.1700
Data Index: 7745784 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4261. Min Range: -6.4261
Max Act: 6.0823. Min Act: -0.1700
Data Index: 1703326 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4261. Min Range: -6.4261
Max Act: 6.0823. Min Act: -0.1700
Data Index: 4375145 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4261. Min Range: -6.4261
Max Act: 6.0511. Min Act: -0.1700
Data Index: 72018 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4261. Min Range: -6.4261
Max Act: 6.0511. Min Act: -0.1700
Data Index: 4419959 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4261. Min Range: -6.4261
Max Act: 5.9886. Min Act: -0.1700
Data Index: 8566623 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4261. Min Range: -6.4261
Max Act: 5.9886. Min Act: -0.1700
Data Index: 5748751 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4261. Min Range: -6.4261
Max Act: 5.9886. Min Act: -0.1700
Data Index: 4113681 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4261. Min Range: -6.4261
Max Act: 5.9886. Min Act: -0.1700
Data Index: 7236354 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4261. Min Range: -6.4261
Max Act: 6.0198. Min Act: -0.1700
Data Index: 6137488 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19