Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 613 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6208. Min Range: -8.6208
Max Act: 8.6208. Min Act: -0.1700
Data Index: 7104774 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6208. Min Range: -8.6208
Max Act: 8.3708. Min Act: -0.1700
Data Index: 5306246 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6208. Min Range: -8.6208
Max Act: 8.1208. Min Act: -0.1700
Data Index: 3826093 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6208. Min Range: -8.6208
Max Act: 8.1208. Min Act: -0.1700
Data Index: 5313010 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6208. Min Range: -8.6208
Max Act: 8.1208. Min Act: -0.1700
Data Index: 1749906 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6208. Min Range: -8.6208
Max Act: 8.0583. Min Act: -0.1700
Data Index: 4555564 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6208. Min Range: -8.6208
Max Act: 7.9958. Min Act: -0.1700
Data Index: 8785797 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6208. Min Range: -8.6208
Max Act: 7.9958. Min Act: -0.1700
Data Index: 6068261 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6208. Min Range: -8.6208
Max Act: 7.9333. Min Act: -0.1700
Data Index: 7120448 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6208. Min Range: -8.6208
Max Act: 7.9333. Min Act: -0.1700
Data Index: 788521 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6208. Min Range: -8.6208
Max Act: 7.9333. Min Act: -0.1700
Data Index: 7953448 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6208. Min Range: -8.6208
Max Act: 7.8708. Min Act: -0.1700
Data Index: 6601464 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6208. Min Range: -8.6208
Max Act: 7.8708. Min Act: -0.1700
Data Index: 55671 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6208. Min Range: -8.6208
Max Act: 7.8708. Min Act: -0.1700
Data Index: 6990583 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6208. Min Range: -8.6208
Max Act: 7.8708. Min Act: -0.1700
Data Index: 8708944 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6208. Min Range: -8.6208
Max Act: 7.8708. Min Act: -0.1700
Data Index: 1078774 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6208. Min Range: -8.6208
Max Act: 7.8083. Min Act: -0.1700
Data Index: 5886016 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6208. Min Range: -8.6208
Max Act: 7.7771. Min Act: -0.1700
Data Index: 5828514 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6208. Min Range: -8.6208
Max Act: 7.8083. Min Act: -0.1700
Data Index: 6047167 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6208. Min Range: -8.6208
Max Act: 7.7771. Min Act: -0.1700
Data Index: 112687 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #19