Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4144 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9711. Min Range: -8.9711
Max Act: 8.9711. Min Act: -0.1700
Data Index: 4198702 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9711. Min Range: -8.9711
Max Act: 8.9711. Min Act: -0.1700
Data Index: 4199338 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9711. Min Range: -8.9711
Max Act: 8.7211. Min Act: -0.1700
Data Index: 4199339 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9711. Min Range: -8.9711
Max Act: 8.7836. Min Act: -0.1700
Data Index: 8061220 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9711. Min Range: -8.9711
Max Act: 8.5961. Min Act: -0.1700
Data Index: 7831525 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9711. Min Range: -8.9711
Max Act: 8.3461. Min Act: -0.1700
Data Index: 6895434 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9711. Min Range: -8.9711
Max Act: 8.3461. Min Act: -0.1700
Data Index: 7224745 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9711. Min Range: -8.9711
Max Act: 8.2836. Min Act: -0.1700
Data Index: 3076645 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9711. Min Range: -8.9711
Max Act: 8.2836. Min Act: -0.1700
Data Index: 4199340 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9711. Min Range: -8.9711
Max Act: 8.3461. Min Act: -0.1700
Data Index: 2188044 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9711. Min Range: -8.9711
Max Act: 8.2836. Min Act: -0.1700
Data Index: 6759651 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9711. Min Range: -8.9711
Max Act: 8.2836. Min Act: -0.1700
Data Index: 2264959 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9711. Min Range: -8.9711
Max Act: 8.2836. Min Act: -0.1700
Data Index: 3121179 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9711. Min Range: -8.9711
Max Act: 8.2211. Min Act: -0.1700
Data Index: 4689788 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9711. Min Range: -8.9711
Max Act: 8.1586. Min Act: -0.1700
Data Index: 3925429 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9711. Min Range: -8.9711
Max Act: 8.2211. Min Act: -0.1700
Data Index: 6490660 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9711. Min Range: -8.9711
Max Act: 8.2211. Min Act: -0.1700
Data Index: 6312697 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9711. Min Range: -8.9711
Max Act: 8.2211. Min Act: -0.1700
Data Index: 1955663 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9711. Min Range: -8.9711
Max Act: 8.1586. Min Act: -0.1700
Data Index: 704577 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9711. Min Range: -8.9711
Max Act: 8.1273. Min Act: -0.1700
Data Index: 832569 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #19