Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1122 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4144. Min Range: -3.4144
Max Act: 3.3988. Min Act: -0.1700
Data Index: 5865853 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4144. Min Range: -3.4144
Max Act: 3.4144. Min Act: -0.1700
Data Index: 7034265 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4144. Min Range: -3.4144
Max Act: 3.3831. Min Act: -0.1700
Data Index: 1751718 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4144. Min Range: -3.4144
Max Act: 3.3517. Min Act: -0.1700
Data Index: 7827327 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4144. Min Range: -3.4144
Max Act: 3.3517. Min Act: -0.1700
Data Index: 7364377 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4144. Min Range: -3.4144
Max Act: 3.3360. Min Act: -0.1700
Data Index: 6353219 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4144. Min Range: -3.4144
Max Act: 3.3360. Min Act: -0.1700
Data Index: 536011 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4144. Min Range: -3.4144
Max Act: 3.3046. Min Act: -0.1700
Data Index: 2695803 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4144. Min Range: -3.4144
Max Act: 3.2732. Min Act: -0.1700
Data Index: 2424747 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4144. Min Range: -3.4144
Max Act: 3.2575. Min Act: -0.1700
Data Index: 4111487 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4144. Min Range: -3.4144
Max Act: 3.2575. Min Act: -0.1700
Data Index: 6540941 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4144. Min Range: -3.4144
Max Act: 3.2418. Min Act: -0.1700
Data Index: 1314850 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4144. Min Range: -3.4144
Max Act: 3.2418. Min Act: -0.1700
Data Index: 3582444 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4144. Min Range: -3.4144
Max Act: 3.2575. Min Act: -0.1700
Data Index: 513248 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4144. Min Range: -3.4144
Max Act: 3.2418. Min Act: -0.1700
Data Index: 6378495 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4144. Min Range: -3.4144
Max Act: 3.2575. Min Act: -0.1700
Data Index: 8541939 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4144. Min Range: -3.4144
Max Act: 3.2104. Min Act: -0.1700
Data Index: 3887314 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4144. Min Range: -3.4144
Max Act: 3.2104. Min Act: -0.1700
Data Index: 4414737 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4144. Min Range: -3.4144
Max Act: 3.2418. Min Act: -0.1700
Data Index: 2520244 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4144. Min Range: -3.4144
Max Act: 3.2261. Min Act: -0.1700
Data Index: 7611075 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #19