Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3984 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9986. Min Range: -4.9986
Max Act: 4.9674. Min Act: -0.1700
Data Index: 214213 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9986. Min Range: -4.9986
Max Act: 4.9986. Min Act: -0.1700
Data Index: 7410638 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9986. Min Range: -4.9986
Max Act: 4.9986. Min Act: -0.1700
Data Index: 6566283 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9986. Min Range: -4.9986
Max Act: 4.9674. Min Act: -0.1700
Data Index: 7711092 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9986. Min Range: -4.9986
Max Act: 4.9361. Min Act: -0.1700
Data Index: 8692384 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9986. Min Range: -4.9986
Max Act: 4.8736. Min Act: -0.1700
Data Index: 4759713 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9986. Min Range: -4.9986
Max Act: 4.8736. Min Act: -0.1700
Data Index: 7404010 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9986. Min Range: -4.9986
Max Act: 4.9049. Min Act: -0.1700
Data Index: 6507094 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9986. Min Range: -4.9986
Max Act: 4.8424. Min Act: -0.1700
Data Index: 6430266 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9986. Min Range: -4.9986
Max Act: 4.8424. Min Act: -0.1700
Data Index: 458914 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9986. Min Range: -4.9986
Max Act: 4.8736. Min Act: -0.1700
Data Index: 421001 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9986. Min Range: -4.9986
Max Act: 4.8736. Min Act: -0.1700
Data Index: 6451544 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9986. Min Range: -4.9986
Max Act: 4.8736. Min Act: -0.1700
Data Index: 1445411 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9986. Min Range: -4.9986
Max Act: 4.8424. Min Act: -0.1700
Data Index: 5246018 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9986. Min Range: -4.9986
Max Act: 4.8424. Min Act: -0.1700
Data Index: 6714642 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9986. Min Range: -4.9986
Max Act: 4.8424. Min Act: -0.1700
Data Index: 7323702 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9986. Min Range: -4.9986
Max Act: 4.8424. Min Act: -0.1700
Data Index: 4468055 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9986. Min Range: -4.9986
Max Act: 4.8424. Min Act: -0.1700
Data Index: 384601 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9986. Min Range: -4.9986
Max Act: 4.8111. Min Act: -0.1700
Data Index: 7599472 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9986. Min Range: -4.9986
Max Act: 4.8111. Min Act: -0.1700
Data Index: 7669454 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19