Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2673 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7970. Min Range: -4.7970
Max Act: 4.7970. Min Act: -0.1700
Data Index: 1741803 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7970. Min Range: -4.7970
Max Act: 4.7345. Min Act: -0.1700
Data Index: 1388615 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7970. Min Range: -4.7970
Max Act: 4.7032. Min Act: -0.1700
Data Index: 1889352 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7970. Min Range: -4.7970
Max Act: 4.7032. Min Act: -0.1700
Data Index: 1889354 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7970. Min Range: -4.7970
Max Act: 4.7032. Min Act: -0.1700
Data Index: 497764 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7970. Min Range: -4.7970
Max Act: 4.6720. Min Act: -0.1700
Data Index: 5036173 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7970. Min Range: -4.7970
Max Act: 4.6720. Min Act: -0.1700
Data Index: 1194092 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7970. Min Range: -4.7970
Max Act: 4.6720. Min Act: -0.1700
Data Index: 8807229 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7970. Min Range: -4.7970
Max Act: 4.6095. Min Act: -0.1700
Data Index: 4330226 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7970. Min Range: -4.7970
Max Act: 4.6407. Min Act: -0.1700
Data Index: 422842 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7970. Min Range: -4.7970
Max Act: 4.5782. Min Act: -0.1700
Data Index: 5108342 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7970. Min Range: -4.7970
Max Act: 4.6095. Min Act: -0.1700
Data Index: 1229743 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7970. Min Range: -4.7970
Max Act: 4.6095. Min Act: -0.1700
Data Index: 4290322 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7970. Min Range: -4.7970
Max Act: 4.6407. Min Act: -0.1700
Data Index: 6566725 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7970. Min Range: -4.7970
Max Act: 4.6095. Min Act: -0.1700
Data Index: 5308240 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7970. Min Range: -4.7970
Max Act: 4.5782. Min Act: -0.1700
Data Index: 2440082 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7970. Min Range: -4.7970
Max Act: 4.5782. Min Act: -0.1700
Data Index: 2510645 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7970. Min Range: -4.7970
Max Act: 4.5470. Min Act: -0.1700
Data Index: 2822715 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7970. Min Range: -4.7970
Max Act: 4.5470. Min Act: -0.1700
Data Index: 5420789 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7970. Min Range: -4.7970
Max Act: 4.5470. Min Act: -0.1700
Data Index: 3485528 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19