Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1240 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4633. Min Range: -5.4633
Max Act: 5.4633. Min Act: -0.1700
Data Index: 2237148 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4633. Min Range: -5.4633
Max Act: 5.3695. Min Act: -0.1700
Data Index: 1502093 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4633. Min Range: -5.4633
Max Act: 5.3383. Min Act: -0.1700
Data Index: 5790378 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4633. Min Range: -5.4633
Max Act: 5.3383. Min Act: -0.1700
Data Index: 3800485 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4633. Min Range: -5.4633
Max Act: 5.3383. Min Act: -0.1700
Data Index: 1341362 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4633. Min Range: -5.4633
Max Act: 5.3070. Min Act: -0.1700
Data Index: 1658524 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4633. Min Range: -5.4633
Max Act: 5.3070. Min Act: -0.1700
Data Index: 5585420 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4633. Min Range: -5.4633
Max Act: 5.3070. Min Act: -0.1700
Data Index: 4098436 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4633. Min Range: -5.4633
Max Act: 5.2758. Min Act: -0.1700
Data Index: 5110399 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4633. Min Range: -5.4633
Max Act: 5.2758. Min Act: -0.1700
Data Index: 3119221 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4633. Min Range: -5.4633
Max Act: 5.2445. Min Act: -0.1700
Data Index: 7781000 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4633. Min Range: -5.4633
Max Act: 5.2133. Min Act: -0.1700
Data Index: 6935150 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4633. Min Range: -5.4633
Max Act: 5.2133. Min Act: -0.1700
Data Index: 8545528 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4633. Min Range: -5.4633
Max Act: 5.2133. Min Act: -0.1700
Data Index: 1222440 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4633. Min Range: -5.4633
Max Act: 5.2133. Min Act: -0.1700
Data Index: 5765600 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4633. Min Range: -5.4633
Max Act: 5.2133. Min Act: -0.1700
Data Index: 331678 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4633. Min Range: -5.4633
Max Act: 5.1820. Min Act: -0.1700
Data Index: 4305798 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4633. Min Range: -5.4633
Max Act: 5.1820. Min Act: -0.1700
Data Index: 7876286 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4633. Min Range: -5.4633
Max Act: 5.1820. Min Act: -0.1700
Data Index: 2062044 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4633. Min Range: -5.4633
Max Act: 5.1820. Min Act: -0.1700
Data Index: 5518113 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19