Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2706 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8013. Min Range: -5.8013
Max Act: 5.8013. Min Act: -0.1700
Data Index: 2521672 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8013. Min Range: -5.8013
Max Act: 5.6763. Min Act: -0.1700
Data Index: 6029692 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8013. Min Range: -5.8013
Max Act: 5.6450. Min Act: -0.1700
Data Index: 1858345 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8013. Min Range: -5.8013
Max Act: 5.5825. Min Act: -0.1700
Data Index: 7452924 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8013. Min Range: -5.8013
Max Act: 5.5513. Min Act: -0.1700
Data Index: 8718110 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8013. Min Range: -5.8013
Max Act: 5.5825. Min Act: -0.1700
Data Index: 3690823 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8013. Min Range: -5.8013
Max Act: 5.5513. Min Act: -0.1700
Data Index: 7274338 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8013. Min Range: -5.8013
Max Act: 5.5513. Min Act: -0.1700
Data Index: 7336508 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8013. Min Range: -5.8013
Max Act: 5.5200. Min Act: -0.1700
Data Index: 7810366 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8013. Min Range: -5.8013
Max Act: 5.5200. Min Act: -0.1700
Data Index: 1152220 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8013. Min Range: -5.8013
Max Act: 5.4888. Min Act: -0.1700
Data Index: 901276 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8013. Min Range: -5.8013
Max Act: 5.4575. Min Act: -0.1700
Data Index: 7054600 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8013. Min Range: -5.8013
Max Act: 5.4575. Min Act: -0.1700
Data Index: 5146109 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8013. Min Range: -5.8013
Max Act: 5.4263. Min Act: -0.1700
Data Index: 921360 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8013. Min Range: -5.8013
Max Act: 5.4263. Min Act: -0.1700
Data Index: 3514833 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8013. Min Range: -5.8013
Max Act: 5.4263. Min Act: -0.1700
Data Index: 281938 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8013. Min Range: -5.8013
Max Act: 5.4263. Min Act: -0.1700
Data Index: 2181978 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8013. Min Range: -5.8013
Max Act: 5.4263. Min Act: -0.1700
Data Index: 4098886 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8013. Min Range: -5.8013
Max Act: 5.4263. Min Act: -0.1700
Data Index: 4445555 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8013. Min Range: -5.8013
Max Act: 5.3950. Min Act: -0.1700
Data Index: 7067233 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19