Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4619 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3907. Min Range: -7.3907
Max Act: 7.3907. Min Act: -0.1700
Data Index: 6026696 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3907. Min Range: -7.3907
Max Act: 6.9532. Min Act: -0.1700
Data Index: 983170 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3907. Min Range: -7.3907
Max Act: 6.8595. Min Act: -0.1700
Data Index: 8784580 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3907. Min Range: -7.3907
Max Act: 6.8282. Min Act: -0.1700
Data Index: 7578186 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3907. Min Range: -7.3907
Max Act: 6.7970. Min Act: -0.1700
Data Index: 2734737 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3907. Min Range: -7.3907
Max Act: 6.7970. Min Act: -0.1700
Data Index: 5930402 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3907. Min Range: -7.3907
Max Act: 6.7657. Min Act: -0.1700
Data Index: 6321492 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3907. Min Range: -7.3907
Max Act: 6.7970. Min Act: -0.1700
Data Index: 2284600 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3907. Min Range: -7.3907
Max Act: 6.7657. Min Act: -0.1700
Data Index: 8807911 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3907. Min Range: -7.3907
Max Act: 6.7657. Min Act: -0.1700
Data Index: 8499789 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3907. Min Range: -7.3907
Max Act: 6.7657. Min Act: -0.1700
Data Index: 2098671 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3907. Min Range: -7.3907
Max Act: 6.6720. Min Act: -0.1700
Data Index: 6774356 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3907. Min Range: -7.3907
Max Act: 6.6720. Min Act: -0.1700
Data Index: 1334611 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3907. Min Range: -7.3907
Max Act: 6.6095. Min Act: -0.1700
Data Index: 7189983 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3907. Min Range: -7.3907
Max Act: 6.6407. Min Act: -0.1700
Data Index: 4606572 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3907. Min Range: -7.3907
Max Act: 6.6095. Min Act: -0.1700
Data Index: 236413 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3907. Min Range: -7.3907
Max Act: 6.6095. Min Act: -0.1700
Data Index: 3710581 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3907. Min Range: -7.3907
Max Act: 6.5782. Min Act: -0.1700
Data Index: 7500823 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3907. Min Range: -7.3907
Max Act: 6.5782. Min Act: -0.1700
Data Index: 691578 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3907. Min Range: -7.3907
Max Act: 6.5782. Min Act: -0.1700
Data Index: 3500914 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #19