Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4604 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4597. Min Range: -6.4597
Max Act: 6.4597. Min Act: -0.1700
Data Index: 7272054 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4597. Min Range: -6.4597
Max Act: 6.3972. Min Act: -0.1700
Data Index: 8160073 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4597. Min Range: -6.4597
Max Act: 6.2097. Min Act: -0.1700
Data Index: 8290509 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4597. Min Range: -6.4597
Max Act: 6.2097. Min Act: -0.1700
Data Index: 3539347 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4597. Min Range: -6.4597
Max Act: 6.1159. Min Act: -0.1700
Data Index: 2230598 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4597. Min Range: -6.4597
Max Act: 6.0847. Min Act: -0.1700
Data Index: 4047649 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4597. Min Range: -6.4597
Max Act: 6.0534. Min Act: -0.1700
Data Index: 5471623 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4597. Min Range: -6.4597
Max Act: 6.0534. Min Act: -0.1700
Data Index: 3922628 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4597. Min Range: -6.4597
Max Act: 5.9909. Min Act: -0.1700
Data Index: 7923926 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4597. Min Range: -6.4597
Max Act: 5.9909. Min Act: -0.1700
Data Index: 5884326 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4597. Min Range: -6.4597
Max Act: 5.9284. Min Act: -0.1700
Data Index: 7843978 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4597. Min Range: -6.4597
Max Act: 5.9597. Min Act: -0.1700
Data Index: 8204117 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4597. Min Range: -6.4597
Max Act: 5.8347. Min Act: -0.1700
Data Index: 6676827 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4597. Min Range: -6.4597
Max Act: 5.8659. Min Act: -0.1700
Data Index: 7843970 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4597. Min Range: -6.4597
Max Act: 5.8347. Min Act: -0.1700
Data Index: 2251731 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4597. Min Range: -6.4597
Max Act: 5.8347. Min Act: -0.1700
Data Index: 7739229 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4597. Min Range: -6.4597
Max Act: 5.8347. Min Act: -0.1700
Data Index: 6864639 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4597. Min Range: -6.4597
Max Act: 5.8347. Min Act: -0.1700
Data Index: 3611969 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4597. Min Range: -6.4597
Max Act: 5.8347. Min Act: -0.1700
Data Index: 760177 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4597. Min Range: -6.4597
Max Act: 5.8034. Min Act: -0.1700
Data Index: 5855210 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19