Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 981 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.5708. Min Range: -7.5708
Max Act: 7.5708. Min Act: -0.1700
Data Index: 3129242 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5708. Min Range: -7.5708
Max Act: 7.4146. Min Act: -0.1700
Data Index: 8223640 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5708. Min Range: -7.5708
Max Act: 6.5396. Min Act: -0.1700
Data Index: 3141008 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5708. Min Range: -7.5708
Max Act: 6.4771. Min Act: -0.1700
Data Index: 5097223 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5708. Min Range: -7.5708
Max Act: 6.4771. Min Act: -0.1700
Data Index: 8675615 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5708. Min Range: -7.5708
Max Act: 6.4458. Min Act: -0.1700
Data Index: 3585528 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5708. Min Range: -7.5708
Max Act: 6.4146. Min Act: -0.1700
Data Index: 3229659 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5708. Min Range: -7.5708
Max Act: 6.3833. Min Act: -0.1700
Data Index: 1979836 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5708. Min Range: -7.5708
Max Act: 6.2896. Min Act: -0.1700
Data Index: 2124433 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5708. Min Range: -7.5708
Max Act: 6.2583. Min Act: -0.1700
Data Index: 3885367 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5708. Min Range: -7.5708
Max Act: 6.1646. Min Act: -0.1700
Data Index: 812157 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5708. Min Range: -7.5708
Max Act: 6.1646. Min Act: -0.1700
Data Index: 3469196 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5708. Min Range: -7.5708
Max Act: 6.1333. Min Act: -0.1700
Data Index: 5485559 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5708. Min Range: -7.5708
Max Act: 6.1333. Min Act: -0.1700
Data Index: 3223795 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5708. Min Range: -7.5708
Max Act: 6.0708. Min Act: -0.1700
Data Index: 3251302 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5708. Min Range: -7.5708
Max Act: 6.1021. Min Act: -0.1700
Data Index: 836778 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5708. Min Range: -7.5708
Max Act: 6.0396. Min Act: -0.1700
Data Index: 1745248 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5708. Min Range: -7.5708
Max Act: 6.0708. Min Act: -0.1700
Data Index: 6402273 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5708. Min Range: -7.5708
Max Act: 6.0708. Min Act: -0.1700
Data Index: 8458814 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5708. Min Range: -7.5708
Max Act: 6.0396. Min Act: -0.1700
Data Index: 4717090 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19