Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1288 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7685. Min Range: -6.7685
Max Act: 6.7685. Min Act: -0.1700
Data Index: 8738458 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7685. Min Range: -6.7685
Max Act: 6.2060. Min Act: -0.1700
Data Index: 7811992 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7685. Min Range: -6.7685
Max Act: 6.1123. Min Act: -0.1700
Data Index: 1619270 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7685. Min Range: -6.7685
Max Act: 6.0810. Min Act: -0.1700
Data Index: 6788703 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7685. Min Range: -6.7685
Max Act: 6.0185. Min Act: -0.1700
Data Index: 5027275 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7685. Min Range: -6.7685
Max Act: 6.0185. Min Act: -0.1700
Data Index: 5236639 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7685. Min Range: -6.7685
Max Act: 5.9873. Min Act: -0.1700
Data Index: 4057329 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7685. Min Range: -6.7685
Max Act: 5.9873. Min Act: -0.1700
Data Index: 4093321 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7685. Min Range: -6.7685
Max Act: 5.9248. Min Act: -0.1700
Data Index: 5641804 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7685. Min Range: -6.7685
Max Act: 5.8935. Min Act: -0.1700
Data Index: 5251607 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7685. Min Range: -6.7685
Max Act: 5.8623. Min Act: -0.1700
Data Index: 324537 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7685. Min Range: -6.7685
Max Act: 5.7998. Min Act: -0.1700
Data Index: 5613188 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7685. Min Range: -6.7685
Max Act: 5.7685. Min Act: -0.1700
Data Index: 860075 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7685. Min Range: -6.7685
Max Act: 5.7685. Min Act: -0.1700
Data Index: 5350763 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7685. Min Range: -6.7685
Max Act: 5.7685. Min Act: -0.1700
Data Index: 5257411 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7685. Min Range: -6.7685
Max Act: 5.7998. Min Act: -0.1700
Data Index: 5214113 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7685. Min Range: -6.7685
Max Act: 5.7685. Min Act: -0.1700
Data Index: 6061438 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7685. Min Range: -6.7685
Max Act: 5.7685. Min Act: -0.1700
Data Index: 3953769 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7685. Min Range: -6.7685
Max Act: 5.7373. Min Act: -0.1700
Data Index: 1927886 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7685. Min Range: -6.7685
Max Act: 5.7685. Min Act: -0.1700
Data Index: 7452080 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19