Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5102 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2967. Min Range: -6.2967
Max Act: 6.2967. Min Act: -0.1700
Data Index: 114880 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2967. Min Range: -6.2967
Max Act: 5.6405. Min Act: -0.1700
Data Index: 2630840 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2967. Min Range: -6.2967
Max Act: 5.5780. Min Act: -0.1700
Data Index: 2275024 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2967. Min Range: -6.2967
Max Act: 5.5780. Min Act: -0.1700
Data Index: 3247749 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2967. Min Range: -6.2967
Max Act: 5.5780. Min Act: -0.1700
Data Index: 4348219 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2967. Min Range: -6.2967
Max Act: 5.5467. Min Act: -0.1700
Data Index: 116617 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2967. Min Range: -6.2967
Max Act: 5.5467. Min Act: -0.1700
Data Index: 2346297 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2967. Min Range: -6.2967
Max Act: 5.5155. Min Act: -0.1700
Data Index: 6114762 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2967. Min Range: -6.2967
Max Act: 5.5155. Min Act: -0.1700
Data Index: 4931077 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2967. Min Range: -6.2967
Max Act: 5.5155. Min Act: -0.1700
Data Index: 8215128 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2967. Min Range: -6.2967
Max Act: 5.5155. Min Act: -0.1700
Data Index: 2161006 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2967. Min Range: -6.2967
Max Act: 5.4530. Min Act: -0.1700
Data Index: 5523214 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2967. Min Range: -6.2967
Max Act: 5.4217. Min Act: -0.1700
Data Index: 7982548 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2967. Min Range: -6.2967
Max Act: 5.4530. Min Act: -0.1700
Data Index: 605623 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2967. Min Range: -6.2967
Max Act: 5.3905. Min Act: -0.1700
Data Index: 2919167 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2967. Min Range: -6.2967
Max Act: 5.3905. Min Act: -0.1700
Data Index: 4677947 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2967. Min Range: -6.2967
Max Act: 5.3905. Min Act: -0.1700
Data Index: 2119444 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2967. Min Range: -6.2967
Max Act: 5.3905. Min Act: -0.1700
Data Index: 2426417 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2967. Min Range: -6.2967
Max Act: 5.4217. Min Act: -0.1700
Data Index: 2356817 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2967. Min Range: -6.2967
Max Act: 5.3592. Min Act: -0.1700
Data Index: 6297383 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19