Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4302 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9680. Min Range: -6.9680
Max Act: 6.9680. Min Act: -0.1700
Data Index: 5212688 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9680. Min Range: -6.9680
Max Act: 6.6868. Min Act: -0.1700
Data Index: 4163212 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9680. Min Range: -6.9680
Max Act: 6.5618. Min Act: -0.1700
Data Index: 1345037 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9680. Min Range: -6.9680
Max Act: 6.5618. Min Act: -0.1700
Data Index: 5166599 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9680. Min Range: -6.9680
Max Act: 6.5305. Min Act: -0.1700
Data Index: 5677850 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9680. Min Range: -6.9680
Max Act: 6.4993. Min Act: -0.1700
Data Index: 7045701 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9680. Min Range: -6.9680
Max Act: 6.4993. Min Act: -0.1700
Data Index: 2658425 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9680. Min Range: -6.9680
Max Act: 6.4993. Min Act: -0.1700
Data Index: 7699289 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9680. Min Range: -6.9680
Max Act: 6.4680. Min Act: -0.1700
Data Index: 6287612 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9680. Min Range: -6.9680
Max Act: 6.4680. Min Act: -0.1700
Data Index: 8320440 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9680. Min Range: -6.9680
Max Act: 6.4680. Min Act: -0.1700
Data Index: 273061 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9680. Min Range: -6.9680
Max Act: 6.4680. Min Act: -0.1700
Data Index: 5776002 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9680. Min Range: -6.9680
Max Act: 6.4680. Min Act: -0.1700
Data Index: 1341203 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9680. Min Range: -6.9680
Max Act: 6.4368. Min Act: -0.1700
Data Index: 2665371 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9680. Min Range: -6.9680
Max Act: 6.4368. Min Act: -0.1700
Data Index: 2379537 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9680. Min Range: -6.9680
Max Act: 6.4368. Min Act: -0.1700
Data Index: 1567939 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9680. Min Range: -6.9680
Max Act: 6.4368. Min Act: -0.1700
Data Index: 7815312 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9680. Min Range: -6.9680
Max Act: 6.4055. Min Act: -0.1700
Data Index: 7410962 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9680. Min Range: -6.9680
Max Act: 6.4055. Min Act: -0.1700
Data Index: 318643 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9680. Min Range: -6.9680
Max Act: 6.3743. Min Act: -0.1700
Data Index: 4762795 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19