Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2950 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2897. Min Range: -6.2897
Max Act: 6.2897. Min Act: -0.1700
Data Index: 2534553 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2897. Min Range: -6.2897
Max Act: 6.1960. Min Act: -0.1700
Data Index: 6863651 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2897. Min Range: -6.2897
Max Act: 6.1335. Min Act: -0.1700
Data Index: 5371618 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2897. Min Range: -6.2897
Max Act: 6.1335. Min Act: -0.1700
Data Index: 8551384 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2897. Min Range: -6.2897
Max Act: 6.0085. Min Act: -0.1700
Data Index: 1216255 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2897. Min Range: -6.2897
Max Act: 5.9460. Min Act: -0.1700
Data Index: 2652841 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2897. Min Range: -6.2897
Max Act: 5.8835. Min Act: -0.1700
Data Index: 3261394 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2897. Min Range: -6.2897
Max Act: 5.8522. Min Act: -0.1700
Data Index: 8522032 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2897. Min Range: -6.2897
Max Act: 5.8210. Min Act: -0.1700
Data Index: 8040586 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2897. Min Range: -6.2897
Max Act: 5.8522. Min Act: -0.1700
Data Index: 483545 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2897. Min Range: -6.2897
Max Act: 5.8522. Min Act: -0.1700
Data Index: 7684312 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2897. Min Range: -6.2897
Max Act: 5.7897. Min Act: -0.1700
Data Index: 4635060 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2897. Min Range: -6.2897
Max Act: 5.7272. Min Act: -0.1700
Data Index: 7146633 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2897. Min Range: -6.2897
Max Act: 5.7272. Min Act: -0.1700
Data Index: 5345584 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2897. Min Range: -6.2897
Max Act: 5.7272. Min Act: -0.1700
Data Index: 2919462 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2897. Min Range: -6.2897
Max Act: 5.7272. Min Act: -0.1700
Data Index: 6429633 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2897. Min Range: -6.2897
Max Act: 5.6647. Min Act: -0.1700
Data Index: 1239600 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2897. Min Range: -6.2897
Max Act: 5.6647. Min Act: -0.1700
Data Index: 2748225 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2897. Min Range: -6.2897
Max Act: 5.6647. Min Act: -0.1700
Data Index: 3290383 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2897. Min Range: -6.2897
Max Act: 5.6647. Min Act: -0.1700
Data Index: 8265151 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19