Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 53 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6677. Min Range: -3.6677
Max Act: 3.6677. Min Act: -0.1700
Data Index: 6435168 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6677. Min Range: -3.6677
Max Act: 3.6207. Min Act: -0.1700
Data Index: 6475502 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6677. Min Range: -3.6677
Max Act: 3.6051. Min Act: -0.1700
Data Index: 1472270 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6677. Min Range: -3.6677
Max Act: 3.6207. Min Act: -0.1700
Data Index: 3729039 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6677. Min Range: -3.6677
Max Act: 3.6051. Min Act: -0.1700
Data Index: 3766650 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6677. Min Range: -3.6677
Max Act: 3.5581. Min Act: -0.1700
Data Index: 233531 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6677. Min Range: -3.6677
Max Act: 3.5425. Min Act: -0.1700
Data Index: 2589013 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6677. Min Range: -3.6677
Max Act: 3.5425. Min Act: -0.1700
Data Index: 8422708 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6677. Min Range: -3.6677
Max Act: 3.5425. Min Act: -0.1700
Data Index: 5370649 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6677. Min Range: -3.6677
Max Act: 3.5112. Min Act: -0.1700
Data Index: 6889648 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6677. Min Range: -3.6677
Max Act: 3.5425. Min Act: -0.1700
Data Index: 7924473 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6677. Min Range: -3.6677
Max Act: 3.5268. Min Act: -0.1700
Data Index: 3842640 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6677. Min Range: -3.6677
Max Act: 3.5112. Min Act: -0.1700
Data Index: 3915865 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6677. Min Range: -3.6677
Max Act: 3.5268. Min Act: -0.1700
Data Index: 1176045 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6677. Min Range: -3.6677
Max Act: 3.5112. Min Act: -0.1700
Data Index: 3916189 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6677. Min Range: -3.6677
Max Act: 3.4955. Min Act: -0.1700
Data Index: 3891075 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6677. Min Range: -3.6677
Max Act: 3.4798. Min Act: -0.1700
Data Index: 3488118 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6677. Min Range: -3.6677
Max Act: 3.4955. Min Act: -0.1700
Data Index: 6502249 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6677. Min Range: -3.6677
Max Act: 3.4798. Min Act: -0.1700
Data Index: 1392847 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6677. Min Range: -3.6677
Max Act: 3.4642. Min Act: -0.1700
Data Index: 614535 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19