Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2271 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4455. Min Range: -8.4455
Max Act: 8.4455. Min Act: -0.1700
Data Index: 8496495 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4455. Min Range: -8.4455
Max Act: 8.3205. Min Act: -0.1700
Data Index: 8496496 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4455. Min Range: -8.4455
Max Act: 8.1955. Min Act: -0.1700
Data Index: 4350190 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4455. Min Range: -8.4455
Max Act: 8.0393. Min Act: -0.1700
Data Index: 5368102 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4455. Min Range: -8.4455
Max Act: 8.0393. Min Act: -0.1700
Data Index: 1265602 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4455. Min Range: -8.4455
Max Act: 7.9768. Min Act: -0.1700
Data Index: 8496493 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4455. Min Range: -8.4455
Max Act: 8.0080. Min Act: -0.1700
Data Index: 5428996 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4455. Min Range: -8.4455
Max Act: 7.9455. Min Act: -0.1700
Data Index: 2463796 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4455. Min Range: -8.4455
Max Act: 7.9143. Min Act: -0.1700
Data Index: 4350188 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4455. Min Range: -8.4455
Max Act: 7.8518. Min Act: -0.1700
Data Index: 8711339 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4455. Min Range: -8.4455
Max Act: 7.8205. Min Act: -0.1700
Data Index: 8184532 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4455. Min Range: -8.4455
Max Act: 7.8205. Min Act: -0.1700
Data Index: 7924043 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4455. Min Range: -8.4455
Max Act: 7.8205. Min Act: -0.1700
Data Index: 7700381 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4455. Min Range: -8.4455
Max Act: 7.7580. Min Act: -0.1700
Data Index: 8463758 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4455. Min Range: -8.4455
Max Act: 7.7580. Min Act: -0.1700
Data Index: 5923926 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4455. Min Range: -8.4455
Max Act: 7.6643. Min Act: -0.1700
Data Index: 2007610 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4455. Min Range: -8.4455
Max Act: 7.6018. Min Act: -0.1700
Data Index: 6367802 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4455. Min Range: -8.4455
Max Act: 7.6018. Min Act: -0.1700
Data Index: 9740 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4455. Min Range: -8.4455
Max Act: 7.6018. Min Act: -0.1700
Data Index: 6129805 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4455. Min Range: -8.4455
Max Act: 7.6330. Min Act: -0.1700
Data Index: 2683322 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #19