Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2673 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3508. Min Range: -3.3508
Max Act: 3.3508. Min Act: -0.1700
Data Index: 4841343 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3508. Min Range: -3.3508
Max Act: 3.1937. Min Act: -0.1700
Data Index: 909506 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3508. Min Range: -3.3508
Max Act: 3.1465. Min Act: -0.1700
Data Index: 4813142 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3508. Min Range: -3.3508
Max Act: 3.1622. Min Act: -0.1700
Data Index: 8434861 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3508. Min Range: -3.3508
Max Act: 3.1150. Min Act: -0.1700
Data Index: 6861071 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3508. Min Range: -3.3508
Max Act: 3.0835. Min Act: -0.1700
Data Index: 3227047 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3508. Min Range: -3.3508
Max Act: 3.0204. Min Act: -0.1700
Data Index: 696242 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3508. Min Range: -3.3508
Max Act: 3.0835. Min Act: -0.1700
Data Index: 3559642 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3508. Min Range: -3.3508
Max Act: 3.0835. Min Act: -0.1700
Data Index: 5526707 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3508. Min Range: -3.3508
Max Act: 3.0835. Min Act: -0.1700
Data Index: 3031482 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3508. Min Range: -3.3508
Max Act: 3.0992. Min Act: -0.1700
Data Index: 2777376 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3508. Min Range: -3.3508
Max Act: 3.0677. Min Act: -0.1700
Data Index: 5887647 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3508. Min Range: -3.3508
Max Act: 3.0362. Min Act: -0.1700
Data Index: 7768598 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3508. Min Range: -3.3508
Max Act: 3.0519. Min Act: -0.1700
Data Index: 7203039 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3508. Min Range: -3.3508
Max Act: 3.0519. Min Act: -0.1700
Data Index: 1563951 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3508. Min Range: -3.3508
Max Act: 3.0835. Min Act: -0.1700
Data Index: 6553234 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3508. Min Range: -3.3508
Max Act: 3.0519. Min Act: -0.1700
Data Index: 5739085 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3508. Min Range: -3.3508
Max Act: 3.0519. Min Act: -0.1700
Data Index: 1996483 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3508. Min Range: -3.3508
Max Act: 3.0362. Min Act: -0.1700
Data Index: 3311000 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3508. Min Range: -3.3508
Max Act: 3.0204. Min Act: -0.1700
Data Index: 3537200 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19