Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 70 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0122. Min Range: -5.0122
Max Act: 5.0122. Min Act: -0.1700
Data Index: 5285400 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0122. Min Range: -5.0122
Max Act: 4.9809. Min Act: -0.1700
Data Index: 56026 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0122. Min Range: -5.0122
Max Act: 4.9497. Min Act: -0.1700
Data Index: 2446736 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0122. Min Range: -5.0122
Max Act: 4.9497. Min Act: -0.1700
Data Index: 6621841 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0122. Min Range: -5.0122
Max Act: 4.9184. Min Act: -0.1700
Data Index: 4611881 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0122. Min Range: -5.0122
Max Act: 4.8872. Min Act: -0.1700
Data Index: 2890929 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0122. Min Range: -5.0122
Max Act: 4.8559. Min Act: -0.1700
Data Index: 2446729 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0122. Min Range: -5.0122
Max Act: 4.8872. Min Act: -0.1700
Data Index: 4659645 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0122. Min Range: -5.0122
Max Act: 4.8559. Min Act: -0.1700
Data Index: 4480629 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0122. Min Range: -5.0122
Max Act: 4.8247. Min Act: -0.1700
Data Index: 3341649 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0122. Min Range: -5.0122
Max Act: 4.8559. Min Act: -0.1700
Data Index: 7283057 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0122. Min Range: -5.0122
Max Act: 4.8559. Min Act: -0.1700
Data Index: 2591554 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0122. Min Range: -5.0122
Max Act: 4.8247. Min Act: -0.1700
Data Index: 5748263 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0122. Min Range: -5.0122
Max Act: 4.8247. Min Act: -0.1700
Data Index: 3099311 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0122. Min Range: -5.0122
Max Act: 4.7934. Min Act: -0.1700
Data Index: 6064594 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0122. Min Range: -5.0122
Max Act: 4.7934. Min Act: -0.1700
Data Index: 1293000 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0122. Min Range: -5.0122
Max Act: 4.7934. Min Act: -0.1700
Data Index: 1293002 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0122. Min Range: -5.0122
Max Act: 4.7934. Min Act: -0.1700
Data Index: 4277538 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0122. Min Range: -5.0122
Max Act: 4.8247. Min Act: -0.1700
Data Index: 6420467 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0122. Min Range: -5.0122
Max Act: 4.7934. Min Act: -0.1700
Data Index: 3972382 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19