Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2314 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9678. Min Range: -2.9678
Max Act: 2.9678. Min Act: -0.1700
Data Index: 4488162 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9678. Min Range: -2.9678
Max Act: 2.8251. Min Act: -0.1700
Data Index: 5847534 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9678. Min Range: -2.9678
Max Act: 2.8251. Min Act: -0.1700
Data Index: 6405929 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9678. Min Range: -2.9678
Max Act: 2.7932. Min Act: -0.1700
Data Index: 6662200 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9678. Min Range: -2.9678
Max Act: 2.7932. Min Act: -0.1700
Data Index: 4113106 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9678. Min Range: -2.9678
Max Act: 2.7614. Min Act: -0.1700
Data Index: 6500128 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9678. Min Range: -2.9678
Max Act: 2.7773. Min Act: -0.1700
Data Index: 3943721 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9678. Min Range: -2.9678
Max Act: 2.7294. Min Act: -0.1700
Data Index: 2822033 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9678. Min Range: -2.9678
Max Act: 2.7134. Min Act: -0.1700
Data Index: 1269310 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9678. Min Range: -2.9678
Max Act: 2.7134. Min Act: -0.1700
Data Index: 7117997 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9678. Min Range: -2.9678
Max Act: 2.7294. Min Act: -0.1700
Data Index: 5560586 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9678. Min Range: -2.9678
Max Act: 2.6974. Min Act: -0.1700
Data Index: 3943720 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9678. Min Range: -2.9678
Max Act: 2.6974. Min Act: -0.1700
Data Index: 6966698 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9678. Min Range: -2.9678
Max Act: 2.6814. Min Act: -0.1700
Data Index: 715512 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9678. Min Range: -2.9678
Max Act: 2.6814. Min Act: -0.1700
Data Index: 5619876 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9678. Min Range: -2.9678
Max Act: 2.6654. Min Act: -0.1700
Data Index: 1774960 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9678. Min Range: -2.9678
Max Act: 2.6814. Min Act: -0.1700
Data Index: 7717642 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9678. Min Range: -2.9678
Max Act: 2.6814. Min Act: -0.1700
Data Index: 8535684 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9678. Min Range: -2.9678
Max Act: 2.6494. Min Act: -0.1700
Data Index: 6796411 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9678. Min Range: -2.9678
Max Act: 2.6494. Min Act: -0.1700
Data Index: 6938589 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19