Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1661 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.9147. Min Range: -8.9147
Max Act: 8.9147. Min Act: -0.1700
Data Index: 8256959 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9147. Min Range: -8.9147
Max Act: 8.9147. Min Act: -0.1700
Data Index: 5977221 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9147. Min Range: -8.9147
Max Act: 8.8522. Min Act: -0.1700
Data Index: 1394073 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9147. Min Range: -8.9147
Max Act: 8.8522. Min Act: -0.1700
Data Index: 6465485 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9147. Min Range: -8.9147
Max Act: 8.7897. Min Act: -0.1700
Data Index: 124216 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9147. Min Range: -8.9147
Max Act: 8.7897. Min Act: -0.1700
Data Index: 5312950 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9147. Min Range: -8.9147
Max Act: 8.7272. Min Act: -0.1700
Data Index: 3474808 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9147. Min Range: -8.9147
Max Act: 8.6647. Min Act: -0.1700
Data Index: 8399575 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9147. Min Range: -8.9147
Max Act: 8.6647. Min Act: -0.1700
Data Index: 8122379 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9147. Min Range: -8.9147
Max Act: 8.6022. Min Act: -0.1700
Data Index: 7678342 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9147. Min Range: -8.9147
Max Act: 8.5397. Min Act: -0.1700
Data Index: 5065122 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9147. Min Range: -8.9147
Max Act: 8.6022. Min Act: -0.1700
Data Index: 343265 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9147. Min Range: -8.9147
Max Act: 8.5397. Min Act: -0.1700
Data Index: 8683984 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9147. Min Range: -8.9147
Max Act: 8.5397. Min Act: -0.1700
Data Index: 6035229 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9147. Min Range: -8.9147
Max Act: 8.4772. Min Act: -0.1700
Data Index: 4666745 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9147. Min Range: -8.9147
Max Act: 8.4772. Min Act: -0.1700
Data Index: 3306928 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9147. Min Range: -8.9147
Max Act: 8.4772. Min Act: -0.1700
Data Index: 4859638 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9147. Min Range: -8.9147
Max Act: 8.4772. Min Act: -0.1700
Data Index: 1204685 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9147. Min Range: -8.9147
Max Act: 8.3522. Min Act: -0.1700
Data Index: 6050566 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9147. Min Range: -8.9147
Max Act: 8.4772. Min Act: -0.1700
Data Index: 2367502 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19