Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3892 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6880. Min Range: -5.6880
Max Act: 5.6880. Min Act: -0.1700
Data Index: 4339767 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6880. Min Range: -5.6880
Max Act: 5.6880. Min Act: -0.1700
Data Index: 4879064 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6880. Min Range: -5.6880
Max Act: 5.6880. Min Act: -0.1700
Data Index: 5722670 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6880. Min Range: -5.6880
Max Act: 5.6255. Min Act: -0.1700
Data Index: 5919148 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6880. Min Range: -5.6880
Max Act: 5.5942. Min Act: -0.1700
Data Index: 3157044 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6880. Min Range: -5.6880
Max Act: 5.6255. Min Act: -0.1700
Data Index: 46443 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6880. Min Range: -5.6880
Max Act: 5.5942. Min Act: -0.1700
Data Index: 7412296 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6880. Min Range: -5.6880
Max Act: 5.5630. Min Act: -0.1700
Data Index: 1375905 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6880. Min Range: -5.6880
Max Act: 5.5630. Min Act: -0.1700
Data Index: 4822193 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6880. Min Range: -5.6880
Max Act: 5.5630. Min Act: -0.1700
Data Index: 4133176 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6880. Min Range: -5.6880
Max Act: 5.5317. Min Act: -0.1700
Data Index: 2599111 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6880. Min Range: -5.6880
Max Act: 5.5005. Min Act: -0.1700
Data Index: 1688042 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6880. Min Range: -5.6880
Max Act: 5.4380. Min Act: -0.1700
Data Index: 1594931 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6880. Min Range: -5.6880
Max Act: 5.4380. Min Act: -0.1700
Data Index: 4728596 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6880. Min Range: -5.6880
Max Act: 5.4380. Min Act: -0.1700
Data Index: 7175415 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6880. Min Range: -5.6880
Max Act: 5.4067. Min Act: -0.1700
Data Index: 8591550 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6880. Min Range: -5.6880
Max Act: 5.4067. Min Act: -0.1700
Data Index: 5386710 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6880. Min Range: -5.6880
Max Act: 5.4067. Min Act: -0.1700
Data Index: 3002359 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6880. Min Range: -5.6880
Max Act: 5.3755. Min Act: -0.1700
Data Index: 2283511 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6880. Min Range: -5.6880
Max Act: 5.4067. Min Act: -0.1700
Data Index: 6654189 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #19