Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 948 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.5362. Min Act: -0.1700
Data Index: 3585498 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.5675. Min Act: -0.1700
Data Index: 3585492 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.5050. Min Act: -0.1700
Data Index: 7973636 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.5050. Min Act: -0.1700
Data Index: 2276009 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.4112. Min Act: -0.1700
Data Index: 7742090 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.4425. Min Act: -0.1700
Data Index: 4773328 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.4112. Min Act: -0.1700
Data Index: 3882044 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.4112. Min Act: -0.1700
Data Index: 7642645 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.4112. Min Act: -0.1700
Data Index: 5144180 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.4112. Min Act: -0.1700
Data Index: 178612 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.3800. Min Act: -0.1700
Data Index: 4279068 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.3800. Min Act: -0.1700
Data Index: 2270362 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.3487. Min Act: -0.1700
Data Index: 3985072 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.3800. Min Act: -0.1700
Data Index: 4248923 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.3487. Min Act: -0.1700
Data Index: 1026829 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.3487. Min Act: -0.1700
Data Index: 3882042 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.3175. Min Act: -0.1700
Data Index: 662579 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.3175. Min Act: -0.1700
Data Index: 3424648 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.3175. Min Act: -0.1700
Data Index: 5520640 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.3487. Min Act: -0.1700
Data Index: 684843 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19