Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3051 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9737. Min Range: -3.9737
Max Act: 3.9737. Min Act: -0.1700
Data Index: 7282204 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9737. Min Range: -3.9737
Max Act: 3.9424. Min Act: -0.1700
Data Index: 2528034 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9737. Min Range: -3.9737
Max Act: 3.8799. Min Act: -0.1700
Data Index: 2836482 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9737. Min Range: -3.9737
Max Act: 3.8799. Min Act: -0.1700
Data Index: 4734849 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9737. Min Range: -3.9737
Max Act: 3.8799. Min Act: -0.1700
Data Index: 4396393 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9737. Min Range: -3.9737
Max Act: 3.8174. Min Act: -0.1700
Data Index: 3198347 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9737. Min Range: -3.9737
Max Act: 3.8486. Min Act: -0.1700
Data Index: 7762195 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9737. Min Range: -3.9737
Max Act: 3.8799. Min Act: -0.1700
Data Index: 3823933 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9737. Min Range: -3.9737
Max Act: 3.8174. Min Act: -0.1700
Data Index: 4173811 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9737. Min Range: -3.9737
Max Act: 3.8174. Min Act: -0.1700
Data Index: 6121281 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9737. Min Range: -3.9737
Max Act: 3.8174. Min Act: -0.1700
Data Index: 4094049 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9737. Min Range: -3.9737
Max Act: 3.7861. Min Act: -0.1700
Data Index: 7630910 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9737. Min Range: -3.9737
Max Act: 3.7861. Min Act: -0.1700
Data Index: 1025364 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9737. Min Range: -3.9737
Max Act: 3.7861. Min Act: -0.1700
Data Index: 3298867 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9737. Min Range: -3.9737
Max Act: 3.7705. Min Act: -0.1700
Data Index: 7752016 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9737. Min Range: -3.9737
Max Act: 3.7705. Min Act: -0.1700
Data Index: 5691473 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9737. Min Range: -3.9737
Max Act: 3.7705. Min Act: -0.1700
Data Index: 7341375 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9737. Min Range: -3.9737
Max Act: 3.7705. Min Act: -0.1700
Data Index: 3788823 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9737. Min Range: -3.9737
Max Act: 3.7392. Min Act: -0.1700
Data Index: 111467 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9737. Min Range: -3.9737
Max Act: 3.7392. Min Act: -0.1700
Data Index: 5748096 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19