Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3689 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1020. Min Range: -6.1020
Max Act: 6.1020. Min Act: -0.1700
Data Index: 5398406 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1020. Min Range: -6.1020
Max Act: 6.0395. Min Act: -0.1700
Data Index: 2744015 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1020. Min Range: -6.1020
Max Act: 6.0082. Min Act: -0.1700
Data Index: 743066 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1020. Min Range: -6.1020
Max Act: 5.9770. Min Act: -0.1700
Data Index: 5548650 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1020. Min Range: -6.1020
Max Act: 5.9770. Min Act: -0.1700
Data Index: 8685966 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1020. Min Range: -6.1020
Max Act: 5.9770. Min Act: -0.1700
Data Index: 5791635 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1020. Min Range: -6.1020
Max Act: 5.9770. Min Act: -0.1700
Data Index: 820783 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1020. Min Range: -6.1020
Max Act: 5.9457. Min Act: -0.1700
Data Index: 2579990 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1020. Min Range: -6.1020
Max Act: 5.9457. Min Act: -0.1700
Data Index: 4531739 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1020. Min Range: -6.1020
Max Act: 5.9145. Min Act: -0.1700
Data Index: 7707658 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1020. Min Range: -6.1020
Max Act: 5.9145. Min Act: -0.1700
Data Index: 3183423 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1020. Min Range: -6.1020
Max Act: 5.8832. Min Act: -0.1700
Data Index: 2688082 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1020. Min Range: -6.1020
Max Act: 5.8832. Min Act: -0.1700
Data Index: 1164535 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1020. Min Range: -6.1020
Max Act: 5.9145. Min Act: -0.1700
Data Index: 8318572 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1020. Min Range: -6.1020
Max Act: 5.8832. Min Act: -0.1700
Data Index: 5647557 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1020. Min Range: -6.1020
Max Act: 5.8832. Min Act: -0.1700
Data Index: 5995278 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1020. Min Range: -6.1020
Max Act: 5.8832. Min Act: -0.1700
Data Index: 1365866 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1020. Min Range: -6.1020
Max Act: 5.8832. Min Act: -0.1700
Data Index: 3708740 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1020. Min Range: -6.1020
Max Act: 5.8832. Min Act: -0.1700
Data Index: 6393255 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1020. Min Range: -6.1020
Max Act: 5.8832. Min Act: -0.1700
Data Index: 4049777 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19