Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2537 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5370. Min Range: -6.5370
Max Act: 6.5370. Min Act: -0.1700
Data Index: 3339350 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5370. Min Range: -6.5370
Max Act: 6.2870. Min Act: -0.1700
Data Index: 1996293 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5370. Min Range: -6.5370
Max Act: 6.1620. Min Act: -0.1700
Data Index: 3055020 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5370. Min Range: -6.5370
Max Act: 6.1620. Min Act: -0.1700
Data Index: 3014486 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5370. Min Range: -6.5370
Max Act: 6.1620. Min Act: -0.1700
Data Index: 5614185 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5370. Min Range: -6.5370
Max Act: 6.1932. Min Act: -0.1700
Data Index: 633361 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5370. Min Range: -6.5370
Max Act: 6.1620. Min Act: -0.1700
Data Index: 7944305 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5370. Min Range: -6.5370
Max Act: 6.1307. Min Act: -0.1700
Data Index: 6097354 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5370. Min Range: -6.5370
Max Act: 6.0995. Min Act: -0.1700
Data Index: 8638736 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5370. Min Range: -6.5370
Max Act: 6.0682. Min Act: -0.1700
Data Index: 4205127 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5370. Min Range: -6.5370
Max Act: 6.0370. Min Act: -0.1700
Data Index: 1658953 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5370. Min Range: -6.5370
Max Act: 6.0370. Min Act: -0.1700
Data Index: 1239778 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5370. Min Range: -6.5370
Max Act: 6.0370. Min Act: -0.1700
Data Index: 8777736 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5370. Min Range: -6.5370
Max Act: 5.9745. Min Act: -0.1700
Data Index: 282467 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5370. Min Range: -6.5370
Max Act: 5.9745. Min Act: -0.1700
Data Index: 8074056 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5370. Min Range: -6.5370
Max Act: 6.0370. Min Act: -0.1700
Data Index: 2702525 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5370. Min Range: -6.5370
Max Act: 6.0370. Min Act: -0.1700
Data Index: 215333 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5370. Min Range: -6.5370
Max Act: 6.0057. Min Act: -0.1700
Data Index: 5781851 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5370. Min Range: -6.5370
Max Act: 6.0057. Min Act: -0.1700
Data Index: 1879612 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5370. Min Range: -6.5370
Max Act: 6.0057. Min Act: -0.1700
Data Index: 1923567 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19