Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2971 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1135. Min Range: -4.1135
Max Act: 4.1135. Min Act: -0.1700
Data Index: 8168565 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1135. Min Range: -4.1135
Max Act: 4.0822. Min Act: -0.1700
Data Index: 4635846 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1135. Min Range: -4.1135
Max Act: 4.0510. Min Act: -0.1700
Data Index: 157625 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1135. Min Range: -4.1135
Max Act: 4.0510. Min Act: -0.1700
Data Index: 752859 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1135. Min Range: -4.1135
Max Act: 4.0197. Min Act: -0.1700
Data Index: 2660667 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1135. Min Range: -4.1135
Max Act: 4.0197. Min Act: -0.1700
Data Index: 4642556 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1135. Min Range: -4.1135
Max Act: 4.0197. Min Act: -0.1700
Data Index: 3366063 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1135. Min Range: -4.1135
Max Act: 4.0197. Min Act: -0.1700
Data Index: 6716038 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1135. Min Range: -4.1135
Max Act: 3.9572. Min Act: -0.1700
Data Index: 3510865 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1135. Min Range: -4.1135
Max Act: 3.9572. Min Act: -0.1700
Data Index: 7546551 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1135. Min Range: -4.1135
Max Act: 3.9885. Min Act: -0.1700
Data Index: 76640 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1135. Min Range: -4.1135
Max Act: 3.9885. Min Act: -0.1700
Data Index: 2007437 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1135. Min Range: -4.1135
Max Act: 3.9572. Min Act: -0.1700
Data Index: 3885911 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1135. Min Range: -4.1135
Max Act: 3.9885. Min Act: -0.1700
Data Index: 4738808 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1135. Min Range: -4.1135
Max Act: 3.9259. Min Act: -0.1700
Data Index: 3223630 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1135. Min Range: -4.1135
Max Act: 3.9259. Min Act: -0.1700
Data Index: 4966381 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1135. Min Range: -4.1135
Max Act: 3.9259. Min Act: -0.1700
Data Index: 1252291 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1135. Min Range: -4.1135
Max Act: 3.9259. Min Act: -0.1700
Data Index: 7344272 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1135. Min Range: -4.1135
Max Act: 3.9259. Min Act: -0.1700
Data Index: 1177861 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1135. Min Range: -4.1135
Max Act: 3.9259. Min Act: -0.1700
Data Index: 1131103 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #19